For the fifteenth year, the IIF, in collaboration with SAS®, is proud to announce financial support for research on improving forecasting methods and business forecasting practice. The award for this year will be (2) $5,000 grants. Learn more about our past grant recipients and their award winning research.

The deadline date for applications is 29 September 2017.

This grant was created in 2002 by the IIF, with financial support from the SAS® Institute, in order to promote research on forecasting principles and practice. The fund is divided to support research on (1) how to improve forecasting methods and (2) business forecasting practice and applications.

To apply for this grant, visit our website.

We are pleased to share the Proceedings and Speaker Videos from our most recent conference, The International Symposium on Forecasting, which took place in Cairns, Australia this past June.

• ISF 2017 Proceedings
• Keynote Speakers on youtube, along with links to their presentations

Artificial intelligence (AI) is the name commonly given to the ability of machines to mimic the human aptitude to reason, solve problems, and learn from experience. Research in this field over the past few decades has spanned many disciplines, including the mathematical, social, and biological sciences.

In his four-part article for Foresight beginning in this issue, Spyros Makridakis

• looks at the challenges of forecasting AI progress and presents what he sees as the forthcoming advances in the field (Part 1);
• examines four major scenarios for the impacts of AI and the actions needed to avoid the potentially negative consequences of these technologies (Part 2);
• explores how AI will affect the competitive landscape to which our business models will have to adapt (Part 3); and
• goes beyond AI to cover intelligence augmentation (IA) and the forthcoming revolution in blockchain technologies (BT), whose implications he believes may be greater than those from the Internet (Part 4).

Part 1, featured in this issue, is entitled Forecasting the Impact of Artificial Intelligence and includes an introduction from Owen Davies of TechCast Global, which employs the collective intelligence of global experts to forecast technology breakthroughs.

Paul Goodwin’s latest Hot New Research column is Forecasting After a Fashion and addresses the challenges of forecasting products with very short life cycles plus the whimsy of rapidly changing tastes and priorities.

Pharmaceutical companies face most of the challenges of new-product forecasting and have traditionally relied on judgmental approaches such as historical analogues. One advantage to forecasters that this industry has over many others is the availability of good data: on patients, prescriptions, and medication use over time. Christian Schäfer and Stephan Brebeck present a promising data-driven approach to Predicting the Uptake Curves of New Drugs—an approach that, among other features, can improve a pharmaceutical firm’s decisions on product promotion.

Forecasting in industry is highly collaborative, both across companies and within the firm. John Mello discusses the major form of external collaboration in his article Principles, Benefits, and Pitfalls of Vendor-Managed Inventory.

On the internal side, Chris Gray and John Dougherty present Part 2 of their examination of Misconceptions, Missteps, and Bad Practices in S&OP. Here they take on mispractices related to metrics, time fences, freezing of forecasts, documentation of assumptions, and the linkage of planning and operations to company strategy.

In response to Gray and Dougherty’s argument over the role of software in S&OP in Part 1 of their article, Bill Tonetti attempts to reconcile different viewpoints in his commentary Do Companies Really Need Software for S&OP?

For every expert that says you don’t need S&OP software, others will say that you do. There is little consensus on this subject, and I have come to believe that there are two primary reasons why experts are polarized on the subject.

IT MAY NOT BE TOO LATE…. There may still be time to join me and a superb group of experienced speakers at the 2017 Foresight Practitioner Conference, November 15-16 at North Carolina State University’s Institute for Advanced Analytics in Raleigh. Presentations will center on the theme Recoupling Forecasting with Inventory Control and Supply Planning. This should be a productive as well as enjoyable professional-development opportunity. For more information, see https://foresight.forecasters .org/2017-conference/

The post Len Tashman previews Fall 2017 issue of Foresight appeared first on International Institute of Forecasters.

MEASURING AND FORECASTING VOLATILITY AND RISK
22-24 May 2018
Barcelona, Spain
Registration opens in late 2017

Topics to be covered:

Contact: FBF Secretariat, Tel: [+39] 055 4685739

The post Short Course Announcement: Measuring and Forecasting Volatility and Risk appeared first on International Institute of Forecasters.

FOR IMMEDIATE RELEASE

CONTACT:
Pam Stroud, Business Director
International Institute of Forecasters
+1.781.234.4077
isf@forecasters.org
www.forecasters.org

38^th International Symposium on Forecasting, June 17-20, 2018 in Boulder, Colorado

Boston, MA, March 8, 2018 – Integrating academic research into forecasting practice is one of the hallmarks of the annual International Symposium on Forecasting (ISF) being held this year, June 17-20 in Boulder, Colorado. The ISF draws the world’s top forecasters and researchers, as both presenters and participants, to learn about and discuss cutting-edge developments in forecasting.

The premiere international conference on forecasting, the ISF showcases the breadth of forecasting sectors. The event features sessions on climate predictability, forecasting electricity demand, prediction of business cycles in real time, financial market volatility, forecast optimality, early warning signals, tourism forecasting, information technology trends, macroeconomic trends and the history of prediction science, among many others.

“The Symposium provides a platform for leading forecasting professionals to reveal their insights into the field. With a stimulating scientific and practitioner program, plenty of networking opportunities, and a fun social program, ISF 2018 will be a memorable event. The City of Boulder has extended a warm welcome to our participants, and offers the opportunity to explore the beauty of the Rocky Mountain National Park, Flatiron Mountains, and enjoy the laid-back welcoming vibe of the City ” says Len Tashman, the General Chair of ISF 2018, and Editor in Chief of, Foresight: The International Journal of Applied Forecasting.

The third annual Arnold Zellner Memorial Keynote Address, named in honor of the late professor emeritus at the University of Chicago, will be delivered by Sir David Hendry, FBA, CStat of Oxford University.

Other notable speakers include John Silvia, Wells Fargo; Diane Coyle, University of Cambridge; Paul Goodwin, University of Bath; and David Orrell, Writer and Mathematician.

To complement the stellar line-up of academic speakers, the ISF Forecasting in Practice Track will meet the professional development needs of business forecasting practitioners. Forecasting practitioners and industry experts will deliver this unique and practical program. Full details are available at https://forecasters.org/isf/program/speakers.

ISF sponsors help us advance the study and practice of forecasting worldwide. We’re grateful for their partnership and contribution to this event: Elsevier, University of Colorado Boulder, Microsoft, University of Denver, SAS, Forecast Pro, EViews, Information and Price Dynamics, University of Bath, and Amazon. For more information on sponsorship opportunities, contact the IIF directly (see contact information below).

Research conducted through the SAS Forecasting Research Grant program will also be presented at this year’s conference, the fourteenth year for this program. Awarded by the IIF with support from SAS, grants totaling $10,000 are given annually for research that advances the field of forecasting.

Individuals and organizations are invited to submit abstracts for the conference through March 17. Discounted early registration rates for the ISF conference are available through April 14 for both IIF members and non-members. Special student rates are also available. Access online registration at https://isf.forecasters.org/register/registration-overview/

For more information about the ISF 2018, see https://forecasters.org/isf/ or contact Pam Stroud, IIF Business Director at isf@forecasters.org, +1.781.234.4077.

About the International Institute of Forecasters (IIF) – The International Institute of Forecasters, founded in 1981, is the preeminent organization for forecasting scholars and practitioners across the globe. The IIF is widely recognized for promoting best practices and advancing the field of forecasting through its workshops, its annual International Symposium on Forecasting, and its two publications, The International Journal of Forecasting and its journal for forecasting practitioner’s Foresight: The International Journal of Applied Forecasting.

The post Press Release: 38th International Symposium on Forecasting appeared first on International Institute of Forecasters.

The prize is generously funded by Professor Tao Hong. This year, we will award the prize to a paper published in the International Journal of Forecasting (IJF) during the period 2015-2016. The prize will be US$1000 plus an engraved plaque. The award committee is Rob J Hyndman, Pierre Pinson and James Mitchell.

Nominations are invited from any reader of the IJF. Each person may nominate up to three papers, but you cannot nominate a paper that you have co-authored yourself. Papers co-authored by Tao Hong or one of the award committee are not eligible for the prize. All nominations are to be accompanied by a short statement (up to 200 words) from the nominator, explaining why the paper deserves an award.

You can see the relevant papers published in the period 2015-2016 on Google Scholar. Of course, a good paper does not always get noticed, so don’t let the citation count sway you too much in nominating what you consider to be the best IJF paper from this period.

Nominations should be sent to Rob Hyndman, by email, by 13 April 2018.

The post IIF Tao Hong Best Paper Award in Energy Forecasting appeared first on International Institute of Forecasters.

The ISF 2018 Organizing Committee would like to extend a thank you to all of our sponsors! Their support of the mission of the International Institute of Forecasters (IIF) allows us to make the annual symposium possible.

Registration is in full swing! Visit the ISF website to learn more about the program and to register.

Please take a moment to visit our sponsors websites and learn more about their mission and role in forecasting.

The post ISF 2018 ~ Thank you to our Sponsors! appeared first on International Institute of Forecasters.

The M4 Forecasting Competition is progressing above initial expectations, with 200 individuals and teams from 42 countries around the world participating -double our initial estimate of 100 contestants! The Prize money has increased to more than $30,000 with the generous contributions of UBER and Amazon, in addition to those of the University of Nicosia and Professor Makridakis.

Comparison between the M3 and M4 competitions:

                                                                    M3                              M4

• Prize Money:                                    Zero                   More than $30,000
• Number of Series                           3,003                           100,000
• Number of Participants/Teams    12                                200
• Number of Countries                        5                                  42

Forecasting competitions are critical for advancing the field and make it practical and relevant [https://robjhyndman.com/hyndsight/forecasting-competitions/]. They are the equivalent of laboratories in physical sciences aimed to prove or invalidate scientific theories. They provide empirical evidence about the accuracy of various methods and the best way to be utilized by organizations for achieving maximum benefits. Towards this direction, we expect that M4 will contribute significantly, given that all the information will become available online, and its emphasis of replicability and reproducibility. We are looking forward to learning as much as possible from its findings and further advancing the field of forecasting.

The post M4 Competition ~ Progress Report appeared first on International Institute of Forecasters.

The post 3-day workshop on R appeared first on International Institute of Forecasters.

Call for papers Special Section on “Forecasting Issues in Developing Economies” International Journal of Forecasting
Deadline for submission: July 17, 2017

Following the 21st IIF workshop in Washington, D.C., we are planning a special section on “Forecasting Issues in Developing Economies” in the International Journal of Forecasting. This is an important topic where little has been written due to data limitations and other challenges. We will consider selected papers from the workshop and new submissions following this open call. Relevant topics include forecasts of macro variables; role of financial variables; energy demand; uncertainty associated with economic forecasting, among others. Papers that deal with methodological issues of relevance to developing economies are also welcome.

All papers will be subject to the standard refereeing process of the journal. Those interested in submitting a paper should email it to Prakash Loungani by July 17, 2017.

Guest editors:
Gloria González-Rivera, University of California, Riverside, gloria.gonzalez@ucr.edu
Prakash Loungani, International Monetary Fund, ploungani@imf.org
Xuguang Simon Sheng, American University, sheng@american.edu

21st IIF workshop agenda

The post Call for Papers: Special Section on “Forecasting Issues in Developing Economies” International Journal of Forecasting appeared first on International Institute of Forecasters.

Recoupling Forecasting with Inventory Control and Supply Planning

• Aris Syntetos, Professor of Operational Research and Operations Management, Cardiff University
• Pete Alle, Vice President Supply Chain, Oberweis Dairy, Inc.
• Ellen Bonnell, Head of Global Statistical Forecasting, Hilti
• John Boylan, Professor of Business Analytics, Lancaster University Management School
• Henry (Hank) Canitz, Director of Product Marketing and Business Development, Logility Inc.
• Gian Leocata, Global Inventory Optimization Manager, Sensient Colors, LLC
• Philip Conlon, Senior Director of Demand Planning, Keurig Green Mountain
• Greg Parlier, retired US Army Colonel
• Shaun Snapp, Managing Editor, Brightwork Research and Analysis
• Bill Tonetti, President and co-founder, Demand Works

Register Now!

The post Foresight Practitioner Conference: Early Bird Registration 31 May appeared first on International Institute of Forecasters.

Henry Canitz, Director of Product Marketing, Logility, Inc.

A forecast is not simply a projection of future business; it is a request for product or a request for resources to ensure supply of a product. This makes forecast accuracy crucial for achieving customer-service goals and ensuring proper utilization of resources.

Supply-chain organizations routinely rank demand-planning immaturity as a major obstacle to meeting their supply chain goals. Typical issues that prevent a company from progressing include overreliance on spreadsheets, inadequate executive-management understanding and support, difficulty in developing expert resources, lack of capabilities such as management-by-exception and what-if scenario analysis, and decentralized execution by isolated business functions.

This is a summary of an article that originally appeared in Issue 41 (Spring 2016) of Foresight: The International Journal of Applied Forecasting. To read Hank’s article in its entirety, https://foresight.forecasters.org/overcoming-barriers/

Henry Canitz will join other speakers – experienced and accomplished forecasters and supply chain professionals – in providing perspectives on how to recouple these critical processes, reaping the benefits of lower costs and better service at the 2017 FORESIGHT PRACTITIONER CONFERENCE taking place November 15-16, 2017 at the Institute for Advanced Analytics North Carolina State University, Raleigh, NC.

The post Foresight Article: Overcoming Barriers to Improving Forecast Capabilities appeared first on International Institute of Forecasters.

The post SAS-IIF Grant to Promote Research on Forecasting appeared first on International Institute of Forecasters.

Professor Tao Hong has generously funded a new research award for the best International Journal of Forecasting (IJF) paper on energy forecasting, to be awarded every two years. The award for 2016 is for papers published within 2013-2014. Next year we will award a paper published in 2015-2016, and we will make the award every two years after that.

The award decision was made by a committee consisting of Professors Pierre Pinson, James Mitchell and Rob J Hyndman.

The first IIF Tao Hong Award goes to Professor Rafał Weron for his 2014 paper “Electricity price forecasting: A review of the state-of-the-art with a look into the future”, IJF 30(4), 1030-1081. To read more about Professor Weron and the award, visit Rob Hyndman’s blog, Hyndsight.

The post IIF Tao Hong Award 2016 appeared first on International Institute of Forecasters.

Every two years the International Journal of Forecasting editors select the “best” paper to have been published in the IJF within the previous two-year period. The Best Paper Award consists of US$1000 and an engraved plaque.

At the recent International Symposium on Forecasting in Cairns, Australia, Rob Hyndman, IJF Editor, announced the awards for the best paper published in the International Journal of Forecasting in the period 2014–2015.

The best paper award goes to Nikos Kourentzes, Fotios Petropoulos and Juan Trapero for their 2014 paper on forecasting across multiple frequencies. The nomination of the paper included the following citation.

The full report on the IJF Best Paper Award, check out Rob Hyndman’s blog, Hyndsight.

The post IJF Best Paper Award, 2017 appeared first on International Institute of Forecasters.

The post ISF 2017 Travel Award Winners appeared first on International Institute of Forecasters.

The IIF Board of Directors is pleased to announce Ralph Snyder, Associate Professor at Monash University, with the title of IIF Fellow, as a distinguished researcher in the field of forecasting. At the International Symposium on Forecasting in June, Ralph Snyder was made a Fellow of the International Institute of Forecasters.

In most years, one or two IIF Fellows are elected, so it is a rare honour. Previous fellows have included the late Robert G Brown, Clive Granger and Arnold Zellner, and the very-much-alive Scott Armstrong, Frank Diebold, Robert Engle, Robert Fildes, David Hendry and Spyros Makridakis.

Ralph Snyder is an Associate Professor in the Department of Econometrics & Business Statistics at Monash University. He is the originator of the innovations state space approach to exponential smoothing. This began with his 1985 paper in the Journal of the Royal Statistical Society Series B entitled “Recursive Estimation of Dynamic Linear Models”. Over the years, he developed the approach leading to his 1997 paper in the Journal of the American Statistical Association entitled “Estimation and Prediction for a Class of Dynamic Nonlinear Statistical Models” published with his two close friends and distinguished IIF fellows Keith Ord and Anne Koehler.

Please join us in congratulating Ralph! Learn more about Ralph and his contributions to the field of forecasting.

The post New IIF Research Fellow Announced – Ralph Snyder appeared first on International Institute of Forecasters.

Recoupling Forecasting with Inventory Control and Supply Planning

The post Foresight Practitioner Conference: Early Bird Registration 30 September appeared first on International Institute of Forecasters.

ATTENTION Teachers of Forecasting!

The IIF is offering prizes to top-performing students in undergraduate and graduate level forecasting courses. Star students will receive $100, a Certificate of Achievement from the IIF, and one year’s free membership of the Institute, with all its attendant benefits.

Here is one of our Student Award programs: Time series forecasting models, taught by Professor Reinaldo Castro Souza

To qualify for the award, the course must (a) be taught by an IIF member, (b) have a substantial forecasting content, and (c) have at least 20 hours contact time. Not more than one award will be made per university.

To participate in the awards program, please email forecasters@forecasters.org with subject “IIF Student Forecasting Awards,” attaching your course syllabus.

In the first instance we are offering 20 awards, though this may be increased depending on the number and quality of applications. We hope to be able to distribute awards widely to participating universities around the world.

The post IIF offering Student Forecasting Awards appeared first on International Institute of Forecasters.

The introduction by Editor Len Tashman offers a comprehensive tutorial on forecast accuracy measurement as well as an overview of the articles in this guidebook, of which these are a sample:

The post New: Foresight Guidebook ~ Forecast Accuracy Measurement appeared first on International Institute of Forecasters.

The International Institute of Forecasters is very happy to announce (the beta version) of a new website , The First Port of Call, that aggregates forecasting-related articles and popular blog posts under one domain.

We plan to expand the material featured in this portal, by adding more journals, blogs and conference presentations in the near future. We hope you find this a useful resource.

If you have any comments or suggestions, please contact:

International Institute of Forecasters
https://forecasters.org/
https://fpc.forecasters.org/

The post Forecasting: Port of Call, a new website appeared first on International Institute of Forecasters.

Forecasting has long been an essential part of OR/MS and is now making a major contribution to the fast-developing area of business analytics. Forecasts are a necessary input into almost all planning decisions, be they long- or short-term, but they are also needed in performance analysis and revenue optimization. Forecasting methods should, therefore, form an important part of all university or practitioner courses in analytics.

This year’s survey reflects changes in the software market, but it also puts greater emphasis on the requirements of the practicing forecaster. Please take a moment to learn more and take the survey:

https://www.informs.org/ORMS-Today/Public-Articles/June-Volume-45-Number-3/Software-Survey-Forecasting-2018

By Robert Fildes, Oliver Schaer and Ivan Svetunkov

The post Forecasting Software Survey, 2018 appeared first on International Institute of Forecasters.

We are planning a Special Section on Food and Agriculture Forecasting

The fast growing world population brings a critical challenge to humanity: how to ensure adequate supply and access to safe, healthy food. Accurate forecasts provide valuable information to help in formulating national food and agricultural policies, and to help agriculture companies and farmers adjust their business strategies. Such forecasts cover production, consumption, stocks, trade and prices of major field crops (e.g., corn, sorghum, barley, oats, wheat, rice, soybeans, and cotton) and livestock (e.g., beef, pork, poultry and eggs, and dairy). This special section is to collect high-quality research that involves theoretical and practical aspects of forecasting in food and agriculture. Specifically, it encourages papers that inspire actionable insights and/or make methodological breakthroughs in this area.

Potential topics include but are not limited to:

• Forecasting methodologies in food and agriculture
• Major field crops forecasting
• Livestock forecasting
• Agri-food products forecasting
• Forecasting in vegetables, fruits and other agriculture commodities
• Agriculture commodities futures market forecasting
• Natural resources forecasting in agriculture and food industry
• Water and energy forecasting in agriculture
• Climate forecasting in agriculture

Submission deadline: 31 December 2018

To submit a paper for consideration for the Special Section, please upload your paper online and include a cover letter clearly indicating that the paper is for the special issue “Food and Agriculture Forecasting”. The webpage for online submission is mc.manuscriptcentral.com/ijf. Instructions for authors are provided at ijf.forecasters.org/authors/. All papers will follow IJF’s double-blind refereeing process. For further information about the Special Section, please contact the guest editors.

Guest Editors

Jue Wang, Chinese Academy of Sciences, China (wjue@amss.ac.cn)
Tao Hong, University of North Carolina at Charlotte, USA (hong@uncc.edu)

The post Call For Papers: Food and Agriculture Forecasting | International Journal of Forecasting appeared first on International Institute of Forecasters.

The International Institute of Forecasters (IIF) grants student travel grants to enable individuals from all over the world to attend the International Symposium on Forecasting. These awards are intended to supplement other sources of funding and do not typically cover all expenses. They are primarily for students in the area of forecasting and secondarily for non-student forecasting researchers and practitioners.

Second Year – Forecasting Summer School ~ Probabilistic Forecasting
All ISF travel award recipients, are also eligible to attend the Forecasting Summer School, 15-16 June 2019. Visit our website to learn more.

To apply for the travel grant, visit ISF Financial Support.  The deadline for applications is 11 February 2019. Notification will take place approximately 3-4 weeks after the deadline date.

The post Travel Award Grant – To Attend ISF 2019 in Thessaloniki, Greece appeared first on International Institute of Forecasters.

The ISF Program Committee invites you to submit abstracts related to the theory and practice of forecasting. Suggested themes and topics and full submission rules are available here.

The deadline date for abstracts is 8 March 2019. Papers on all aspects of forecasting are welcome and may be submitted online at isf.forecasters.org/submissions/abstracts/

We encourage you to register early! If you have submitted an abstract, you must register in order to be included in the ISF program.

The International Symposium on Forecasting (ISF) is the premier international event for professional forecasters. The ISF has earned its stellar reputation over the past four decades for the important forecasting research presented there, and for hosting the most highly distinguished experts in the forecasting field. And, in addition to its superb academic and business presentations, the ISF provides many excellent opportunities for networking, learning, and fun. We invite you to join us at the 39th ISF in beautiful Thessaloniki, Greece for four days of keynote speaker presentations, academic sessions, workshops, and social programs.

The post Final Call for Papers: 39th International Symposium on Forecasting appeared first on International Institute of Forecasters.

The ISF 2019 Organizing Committee would like to extend a thank you to all of our sponsors! Their support of the mission of the International Institute of Forecasters (IIF) allows us to make the annual symposium possible. Please take a moment to visit our sponsors websites and learn more about their mission and role in forecasting.

We invite you to join us at ISF 2019 for three days of academic and practitioner speaker presentations, sessions, workshops, and social programs.

REGISTER NOW – Become a member of the IIF & SAVE on registration! Special rates for students and retired professionals are also available.

ISF 2019 Sponsors

The post ISF 2019 ~ Thank you to our Sponsors appeared first on International Institute of Forecasters.

For the sixteenth year, the IIF, in collaboration with SAS®, is proud to announce financial support for research on improving forecasting methods and business forecasting practice. The award for this year will be (2) $5,000 grants.

The deadline date for applications is 29 September 2018.

This grant was created in 2002 by the IIF, with financial support from the SAS® Institute, in order to promote research on forecasting principles and practice. The fund is divided to support research on (1) how to improve forecasting methods and (2) business forecasting practice and applications. To learn more and to apply for this grant, visit our website.

Last year’s award recipients:

Cong Feng and Jie Zhang, The University of Texas at Dallas, for the project proposal in the category of Business Applications Hierarchy-based Disaggregate Forecasting Using Deep Machine Learning in Power System Time Series.

Fernando Cyrino and Bruno Q. Bastos, Pontifical Catholic University of Rio de Janeiro, for the project proposal in the category of Methodology Forecasting Wind and Solar Time Series with Convolutional Neural Networks Approach to Spatio-Temporal.

The post SAS-IIF Grant to Promote Research on Forecasting appeared first on International Institute of Forecasters.

Aris, Pam and George

ISF 2019 – General Chair Overview
George Athanasopoulos, General Chair
Aris Syntetos, Program Chair

The 39th International Symposium on Forecasting (ISF2019) was a great success. ISF 2019 took place at Makedonia Palace Hotel in Thessaloniki, Greece, a truly five-star venue in a magnificent location. The attendance was the largest ever recorded with more than 440 attendees, and an international representation from 44 countries over five continents.

The program was stimulating with a distinguished roster of 3 keynote and 3 featured speakers, a diverse set of Sunday workshops, a fascinating two-day summer school and a large number of excellent presentations in the academic and practitioner tracks covering many different areas of academic research and practice, such as water, energy and environment, macroeconomics, neural networks and machine learning, judgment, tourism, finance, supply chain forecasting, forecasting for social good, and demand forecasting among many others.

We were delighted to observe the high level of participation of practitioners, with 1/3 of the participants coming from Industry. Such a mix of academics and practitioners truly reflects the very mission of the IIF which is to bridge the gap between the theory and practice of forecasting. Practitioners were exposed to the latest academic thinking, and academics (like us) left the conference with a bunch of new relevant research questions to pursue.

Last year the IIF initiated IIF sections, interest groups devoted to advancing the theory and practice of specialized domains of forecasting. In this year’s symposium SWEET (IIF Section on Water, Energy, and EnvironmenT) was extremely active with 13 sessions and 43 talks falling under its umbrella. We are thankful to the great work of Tao Hong and his team for putting these together. Also for the first time we had the IIF ECR (Early Career Researchers) network in action. Over 70 ECRs attended the meet and greet welcome reception, and the two panel sessions organized by the network with the help of the conference and program chairs. We are thankful to the ECR team of Shari De Baets, Anna Sroginis and Michał Chojnowski. We encourage all IIF members to participate in the initiative of Sections. This is a great opportunity for the IIF members to help shape the program of future symposiums and to build a home for their fellow forecasters. Proposals to establish sections should be submitted to Pam Stroud and Tao Hong.

The program continued in the format introduced in 2017 with a full day on Monday, half day on Tuesday followed by the Gala event, and a full day on Wednesday concluding with the closing ceremony which featured an excellent panel discussion on “Advancing forecasting research and practice” followed by other important formalities. This new format has worked very well with close to 300 attendees being present in the very final session.

It is also the 3rd symposium in a row that a fully electronic program was provided through the whova app making it easy to make announcements, provide updates, etc., and also importantly saving the environment. The feedback was extremely positive and it seems that the app has now been fully embraced with more than 95% of the attendees having downloaded it and using it throughout the symposium.

The social program this year was also an amazing success. The Gala event combined a guided tour of the archeological museum of Thessaloniki, followed by dinner at the Polis Convention Center. A record breaking 378 people attended. The presentation of music, instruments and dances from around Greece was followed by the longest line ever of forecasters dancing Zorba. The party and dancing continued until well past midnight. On Thursday 111 people, attended the post-conference tour at Meteora. We also had partner’s tours during the conference which were all well attended.

The support of our sponsors and exhibitors is always key to the success of the symposium, especially in assisting with keeping costs low for our attendees such as the Gala event but also for supporting new initiatives such as the welcome event for the ECR Network.

We are indebted to (gold sponsor) Monash University and in particular to the Monash Business School, (practitioner track sponsor) Google, (invited practitioner sponsor) Microsoft, along with (premium sponsors) Elsevier, Amazon, RiskLabs Australia, EViews and (contributing sponsors) University of Macedonia, International Association of Applied Econometrics, Uber, Timberlake Consultants, Forecast Pro, Wessex, Erasmus School of Economics, Cardiff Business School, SAS and YaleBooks.

Save the date! ISF 2020 in Rio de Janeiro, July 5-8th!

(l-r): General Chair 2019, George Athanasopolous; General Chair 2020, Reinaldo Souza

The post ISF 2019 – In Review appeared first on International Institute of Forecasters.

The post AI: the hype and the promise for forecasting appeared first on International Institute of Forecasters.

The newest Foresight guidebook, Artificial Intelligence (AI), is now available. AI is the name commonly given to the capacity of machines for mimicking the human aptitude to reason, solve problems, and learn from experience. The impact of exponential advances in AI and robotics on future employment prospects is a huge concern with profound implications, and it will almost certainly disrupt forecasting roles. This Foresight guidebook examines how AI will affect organizations, jobs, forecasting, and planning.

ORDER NOW!

• The track record of earlier predictions of the digital revolution
• Potential effects of AI on businesses, manufacturing, and commerce
• Blockchain (BC) technology
• Emerging and long-term future

• Deep learning for forecasting
• Current trends and challenges

The post New Guidebook: Artificial Intelligence appeared first on International Institute of Forecasters.

Lecturer (Assistant Professor) in Business Analytics and Forecasting

The University of Bath School of Management are seeking to appoint a new colleague as a Lecturer in Business Analytics & Forecasting within the Information, Decisions and Operations Division (IDO). Applications are welcome from outstanding candidates with research interests in any IDO-related area, however, candidates must be able to lead pedagogical thinking and deliver inspiring teaching within the areas of Business Analytics & Forecasting.

You would be joining the IDO division, a globally influential group of researchers and teachers. Our research areas include supply chain management, manufacturing and service operations management, operational research, forecasting and mathematical modelling, human aspects of cybersecurity and information systems, and computational social science/data analytics, with a core focus on applying inter-disciplinary insights to tackle significant, real-world, business and social challenges. We are also home to research centres focused on Supply Chain Management (HPC Supply Chain Innovation Lab), Healthcare Innovation (CHI2) and EPSRC and ESRC funded projects ranging from human aspects of cybersecurity to complex project management.

In addition to the research role, you will contribute to our range of highly rated undergraduate and postgraduate offerings.

For full job posting, click here.

Informal enquiries may be made to Professor Michael Lewis (Head of Division), M.A.Lewis@bath.ac.uk, or Dr. Maria Battara, mb2182@bath.ac.uk.

Interviews are expected to take place on Thursday 30th January 2020.

The post Job Opportunity: University of Bath, Assistant Professor, Business Analytics and Forecasting appeared first on International Institute of Forecasters.

About Kinaxis

Companies around the world rely on RapidResponse, our cloud-based platform, to manage their supply chains, monitor risks and opportunities, and respond at the pace of change. At Kinaxis, we’re constantly breaking new ground, using new technology to push the limits of what software can do, including how quickly it can handle big data. Our platform ensures that the products we need – everything from medicine and cars, to day-to-day items like toothpaste – make it to market and into our hands when we need them.

We are looking for – Academic Program Manager 

Reporting to the VP of Industry Outreach and Thought Leadership, the Academic Program Manager is responsible for developing and managing an academic program for Kinaxis, both to have a presence in the classroom as well as align with academic thought leaders defining a top research agenda. S/he will lead the effort to have curriculum developed around our RapidResponse platform, engage in outreach to leading university programs, manage these relationships to ensure success, cultivate relationships with academic experts in areas aligned with Kinaxis, and evangelize our academic outreach externally.

For more information and to apply, visit Kinaxis’ Career Opportunities

If you want to be part of a team that challenges you, moves fast, improves constantly, and makes a difference, let’s talk. For more information, visit the Kinaxis web site at www.kinaxis.com or the company’s blog at http://blog.kinaxis.com/.

The post Job Opportunity: Academic Program Manager, Kinaxis appeared first on International Institute of Forecasters.

Professor Spyros Makridakis is renowned as one of the world’s leading forecasting experts and organizer of the Makridakis Competitions. On behalf of Professor Makridakis, Director of the Institute For the Future (IFF), University of Nicosia (UNIC) it is an honor and a pleasure to introduce you to the Makridakis Forecasting Centre.

M APPLIED FORECASTING COURSE

The M Applied Forecasting Course is a six week online course, (next intake 10 February 2020) covering all types of forecasting, both time series and regression, offering concrete insights on how to improve the accuracy of their predictions, estimate uncertainty realistically and consider its implications to risk.

The most important advantage of the course is its emphasis on hands-on learning by persuading participants to use actual data to both predict and estimate the uncertainty of their forecasts and its implication to risk. This course will offer students the opportunity to harness 40 years of Professor Makridakis knowledge and experience and master forecasting, in six weeks. In addition, Nassim Nicholas Taleb will discuss fat-tails and their implications to uncertainty and risk while Dr. Vangelis Spiliotis will present popular forecasting software and how they can be used. There will also coverage of topics such as Machine Learning (ML), Deep Learning (DL), Cross Learning (CL) and forecasting for intermittent demand.

Forecasts are needed for setting up inventory levels, constructing production or delivery schedules and in all types of planning: from budgeting to strategic. This course covers all types of forecasts and offers concrete information on how to improve the accuracy of and assess the uncertainty of business predictions.

Week 1: The Basis of Forecasting

Week 2: Data for Forecasting and the Assessment of Uncertainty

Week 3: Statistical Methods and Benchmarks

Week 4: Regression (Explanatory) and ML/DL Methods

Week 5: Statistical and ML/DL Forecasting Packages

Week 6: (a) Forecasting Applications (statistical/intermittent demand and ML/DL) (b) Fat-Tailed Uncertainty and Related Risks

EXPLOIT THE VALUE of forecasting to improve your future oriented decisions

LEARN ABOUT the findings of the M Competitions and how they can be applied to improve forecasting

BETTER UNDERSTAND and correctly assess future uncertainty and its implications to risk

CONSTANTLY UPDATE your knowledge with developments and live Q&A sessions with the instructors 

Take advantage of the Early Bird Discount on course fees reducing tuition from €2,000 to €1,420 (until 31 December 2019) and receive a complimentary copy of Professor Makridakis Special Issue of the International Journal of Forecasting with its 35 papers describing all aspects of the M4 Competition. No previous statistical knowledge is required to follow this course.

M5 COMPETITION

The M5 Competition is the latest of the M Competitions (March 2 to 30 June 2020). The competition will use actual/authentic data made generously available by Walmart and will be implemented using Kaggle’s Platform. Given the large number of companies that have already shown interest in participating and the substantial $100,000 prize money, we estimate that the M5 Competition will attract more than 2,000 participants and teams to compete as well as a number of invited companies.

M5 CONFERENCE

Following the M5 Competition, the M5 Conference will present and analyze the findings of the most accurate winning forecasting methods as well as suggest how what has been learned from the competition can be implemented into future forecasting methods.

M5 PUBLICATION

Similar to the M4 Publication that includes 35 papers covering all aspects of the M4 Competition and Conference, there will be a special issue devoted to the M5 Competition & Conference, focusing on how what has been learned can be integrated and applied in practice, published in the International Journal of Forecasting. Practitioners will be invited to submit their articles, comments and suggestions on how future competitions can be improved.

The Makridakis Open Forecasting Centre (MOFC) is non-profit in nature and any financial sponsorships, contributions or donations will be used for forecasting research purposes to enhance future forecasting methods as well as for prizes for the M Competition winners.

Please follow the link to sign up for the M Applied Forecasting Course or get in touch for more information on how you can participate in the M5 Competition or Conference.

CONTACT:
Nick Assimenos
Manager, Institutional & Corporate Partnerships
Institute For the Future (IFF) at University of Nicosia (UNIC)
t +357 22 367203   m +357 99 620085

The post M Applied Forecasting Course | Guest Blog appeared first on International Institute of Forecasters.

The post Forecasting training for the National Health Service (NHS), United Kingdom appeared first on International Institute of Forecasters.

2^nd International workshop on Forecasting for Social Good
Call for Abstracts11-12 June 2020
Kedge Business School, Bordeaux, France

Sponsored by the International Institute of Forecasters (IIF), the workshop on Forecasting for Social Good is now accepting abstracts, both oral and poster presentations. Abstracts on academic forecasting research and applications in forecasting practice are welcome. For poster presentations, upload your poster (PDF) in addition to the abstract. Submit your abstract at Easychair.

If you would like to organise a special session or a panel, contact: Bahman Rostami-Tabar

Important dates

• Submission deadline: March 20, 2020
• Notification to authors: March 27, 2020
• Registration deadline: April 15, 2020

Keynote speakers:

• Spyros Makridakis,University of Nicosia
• Laura Albert, University of Wisconsin Madison
• Nicholas G. Reich, UMass Amherst
• Dr. Leonardo Milano, Centre for Humanitarian Data, United Nations Office for the Coordination of Humanitarian Affairs (OCHA)

About Forecasting for Social Good workshop

Following up on a successful workshop in Cardiff, UK and International Journal of Forecasting’s special issue on Forecasting for Social Good we are pleased to announce the 2nd biannual Workshop on Forecasting for Social Good in 11-12 June 2020 at Kedge Business School in Bordeaux, France.

While there is a growing recognition by agencies, organizations, and governments that data-driven decision-making tools, like forecasting models, can offer significant improvements to the societies they are working to improve, there is not a cohesive body of research that offers guidance on how to best implement, understand, use, and evaluate forecasting methods for societal impact in practice. Furthermore, the research on forecasting for social good has been relatively slow and sporadic, both in academic publications and practical applications. The goal of this workshop is thus to improve the research and practice in issues related to forecasting for social good by: facilitating interactions between practitioners, researchers, and policy makers to develop a cohesive and sustainable network of international collaborations with a focus on issues related to forecasting for social good; promoting the development of new methodology and metrics to address the specific challenges related to forecasting for social good; providing professional development to policy makers; gaining a better understanding of the available data, challenges in data acquisition, and the uncertainty present in the data used to produce forecasts; and, addressing the ethical issues related to the use of forecasting methods for problems that impact society.

The post 26th IIF Workshop: Forecasting for Social Good appeared first on International Institute of Forecasters.

1st ECR webinar — Career opportunities after graduation

Presenter: Tim Januschowski, Manager, AWS
Location: Online
Time: 28 Jan 2020, 5 PM CET / 4 PM GMT / 11 AM EST / 10 AM CST / 8 AM PST
Organizers: ECR, IIF group https://www.linkedin.com/showcase/15808713
Duration: 1 hour
Cost: free

Early Career Researchers, a section of the International Institute of Forecasters (IIF), proudly presents a series of webinars covering career opportunities after graduation. Our first speaker is Tim Januschowski – a manager in Machine Learning Science at Amazon Web Services (AWS). Tim is an expert in forecasting specialized time-series using advanced deep-neural networks models. His presentation will cover what types of forecasting are needed at Amazon, as well as talk about his career. Please feel free to share your questions beforehand or during the talk!

The post Early Career Researchers (ECR) webinar: Career opportunities after graduation appeared first on International Institute of Forecasters.

International Journal of Forecasting: Special Section

The 2^nd international workshop on forecasting for social good, co-sponsored by the IIF, will take place in Bordeaux, France on 11-12 June 2020. The aim of this workshop is aligned with the IIF objectives of international collaboration, bridging the gap between practitioners and academics, professional development of policy makers, and unifying the community of forecasters with a focus on issues of social good.

Evidence from the first IIF workshop on forecasting for social good (Cardiff, 2018) indicated that less attention has been given to research on forecasting for social good in comparison to other areas of forecasting. To address this issue, we have hosted the first workshop, organised three invited sessions at ISF2019, and will be following up with a special issue of the IJF. The purpose of the special section is to attract high quality papers that are concerned with forecasting for social good.

Areas of interest include, but are not limited to:

• Health and healthcare
• Wellbeing
• Humanitarian operations
• Disaster relief
• Education
• Social services
• Environment
• Sustainability
• Public welfare
• Fraud, collusion, and corruption
• Government
• Public safety and security
• Poverty
• Inequality

Submission period
15 June – 18 December 2020

Guidelines
To submit a paper for consideration for this issue, upload your paper online and include a cover letter clearly indicating that the paper is for the issue “Forecasting for Social Good.” Instructions for authors can be found at www.forecasters.org/ijf/authors. All papers will follow IJF’s double-blind refereeing process.

Guest Editors

Dr. Bahman Rostami-Tabar, Cardiff University, UK
Dr. Michael Porter, University of Virginia, USA
Prof. Zied Babai, Kedge Business School, France
Prof. Pierre Pinson, IJF Editor in Chief, Technical University of Denmark

The post Call for Papers: Forecasting for Social Good appeared first on International Institute of Forecasters.

The International Institute of Forecasters will grant travel awards to enable researchers to attend the International Symposium on Forecasting in Rio de Janeiro, July 5-8, 2020. They are primarily for students and early career researchers in the area of forecasting.

The criteria for acceptance of travel award applications include the quality of the submission, how helpful attending the conference might be to the applicant’s research agenda, and whether or not the paper might be publishable in the International Journal of Forecasting.

The application deadline is 24 February 2020. Applications will be reviewed by a committee of IIF Directors. Notification will take place approximately 4 weeks after the deadline date. Applications can be submitted online.

The post ISF 2020 accepting applications for travel awards appeared first on International Institute of Forecasters.

Forecasting Summer School ~ Renewable Energy Forecasting – Theory and Practice
When: July 4-5, 2020
Where: Pontifical Catholic University, Rio de Janeiro, Brazil

The IIF is pleased to announce the 3rd Forecasting Summer School. This year’s topic is Renewable Energy Forecasting – Theory and Practice, taught by instructors Henrik Madsen and Peder Bacher, Technical University of Denmark. Anyone interested in time series analysis and forecasting techniques is welcome to apply.

The course will take place the weekend before our annual conference, the International Symposium on Forecasting. We encourage both students and professionals to participate in both events. Learn more about the instructors, program schedule and submit your application at forecasters.org/events/summer-school. The deadline for applications is April 5, 2020.

We offer 12 full grants for the school program in conjunction with the ISF travel award grant program. When submitting your application for the travel award, indicate that you would like to attend the Summer School. The deadline for applications is February 24, 2020.

Contact:

Pilar Poncela, Professor in Econometrics, Universidad Autonoma de Madrid
Forecasting Summer School 2020  organizer

Pam Stroud, IIF Business Director

The post Forecasting Summer School | Renewable energy appeared first on International Institute of Forecasters.

The post Call for abstracts, 40th International Symposium on Forecasting appeared first on International Institute of Forecasters.

FOR IMMEDIATE RELEASE

CONTACT:

Pam Stroud, Business Director
International Institute of Forecasters
+1.781.234.4077
isf@forecasters.org
www.forecasters.org

40th International Symposium on Forecasting, July 5-8, 2020 in Rio de Janeiro, Brazil

Boston, Mass., March 3, 2020 — Integrating academic research into forecasting practice is one of the hallmarks of the annual International Symposium on Forecasting (ISF), being held this year from July 5-8 in Rio de Janeiro, Brazil. The ISF draws the world’s top forecasters and researchers, as presenters and participants, to learn about and discuss the latest advances in forecasting.

Considered the forecasting field’s premier international conference, the ISF showcases the full scope of forecasting sectors. The event features sessions on climate predictability, forecasting electricity demand, forecasting in business and supply chains, financial-market volatility, forecast optimality, early warning signals, tourism forecasting, information technology trends, macroeconomic trends, and forecasting for public good, among many others.

“The symposium provides a platform for leading forecasting professionals to reveal their insights into the field. With a stimulating scientific and practitioner agenda, plenty of networking opportunities, and a fun social program, ISF 2020 will be a memorable event. The city of Rio has extended a warm welcome to our participants and offers the opportunity to explore the beauty of the coastline, the Copacabana, world cultural landmarks, and the welcoming charm of the city,” says Reinaldo Castro Souza, General Chair of ISF 2020 and IIF Director.

The biennial Arnold Zellner Memorial Keynote Address, named in honor of the late professor emeritus at the University of Chicago, will be delivered by Andrew Harvey, University of Cambridge.

Other notable speakers include Andreas Graefe, Macromedia University; Rob Hyndman, Monash University; Henrik Madsen, Technical University of Denmark; Esther Ruiz, Universidad Carlos III de Madrid; and Rafal Weron, Wroclaw University of Science and Technology.

In addition to this stellar line-up of academic speakers, the 40th ISF will present the ISF Forecasting in Practice Track to meet the professional development needs of business-forecasting practitioners. Forecasting professionals and industry experts from Facebook, Google, SAS, and Uber will deliver this unique and practical program. Full details are available at https://forecasters.org/isf/program/speakers.

ISF sponsors help us advance the study and practice of forecasting worldwide. We’re grateful for their partnership and contributions to this event: Elsevier, Google, Amazon, Grupo Energisa (Brazil), Itaú Bank, EViews, Brazilian National Council for Scientific and Technological Development, PUC-Rio, Timberlake Consultants, SAS, and IAAE. For more information on sponsorship opportunities, contact the IIF (see contact information below).

In conjunction with the ISF, the 3rd Forecasting Summer School will be offered July 4-5. The topic is Renewable Energy Forecasting – Theory and Practice, taught by Henrik Madsen, Technical University of Denmark. Applications are being accepted, https://forecasters.org/events/summer-school/.

Individuals and organizations are invited through March 16 to submit abstracts for the symposium. Discounted early registration rates for the ISF conference are available through May 1 for IIF members and nonmembers. Special student and local resident rates are also available. Access online registration at https://isf.forecasters.org/register/registration/

For more information about ISF 2020, see https://forecasters.org/isf/ or contact Pam Stroud, IIF Business Director, at isf@forecasters.org, +1.781.234.4077.

About the International Institute of Forecasters (IIF) — The International Institute of Forecasters, founded in 1981, is the preeminent organization for forecasting scholars and practitioners worldwide. The IIF is universally recognized for promoting best practices and advancing the field of forecasting through its workshops, its annual International Symposium on Forecasting, and its two publications, The International Journal of Forecasting and, for forecasting practitioners, Foresight: The International Journal of Applied Forecasting.

The post Press Release: 40th International Symposium on Forecasting appeared first on International Institute of Forecasters.

Press Release
04.02.2020

UNIC, Walmart, and Kaggle
Launch M5 Forecasting Competition

The premier academic forecasting competition returns in service of advancing the theory and practice of forecasting, with thousands of individuals and teams anticipated to be competing for $100,000 in prizes. Google, Uber, IIF, MOFC, INSEAD and NTUA are providing financial or academic support.

The University of Nicosia (UNIC) is proud to announce its partnership with Google, Walmart, and Kaggle, in launching two complementary challenges as part of the 5th edition of the M Competition, the premier academic forecasting competition in the world, initiated by Professor Spyros Makridakis 38 years ago.

The M5 will go further than the previous M Competitions in several directions, with the support of the initiative’s new global partners. In the first instance, this latest edition will run two parallel competitions, on “Forecasting Accuracy” and (for the first time explicitly) on “Forecasting Uncertainty”, offering participants the opportunity to enter one or both and be judged across tailored evaluation metrics. Coupled with this, the M5 will include explanatory and exogenous variables to improve forecasting accuracy and the estimation of uncertainty, as well as consider data that display intermittency, i.e. sporadic, inventory sales including zeros. Equally important, the competitions will be based on hierarchical, daily, real data made generously available by the multinational retail corporation Walmart, while hosted on Kaggle, the world’s largest data science community platform.

The M5 will run between 2 March and 30 June 2020, under the scientific direction of the newly-established Makridakis Open Forecasting Center (MOFC) at the University of Nicosia, with the support of invaluable returning academic co-organizers: The Forecasting & Strategy Unit at the National Technical University of Athens (NTUA), and the Centre for Decision Making and Risk Analysis at INSEAD.

Professor Anil Gaba, Director of the Centre for Decision Making and Risk Analysis at INSEAD, underscored the history INSEAD shares with the M Competitions and its creator: “We are interlinked with the Makridakis Forecasting Competitions, having facilitated the M1, M2, and M3 during Professor Makridakis’ tenure at INSEAD. We are proud to be supporting the greatly expanded and highly influential M5 this year, continuing that long tradition”. On his part, the Director of the Forecasting & Strategy Unit at NTUA, Professor Vassilis Assimakopoulos, highlighted the exceptional collaboration and results in the 2018 edition of the competition: “The M4 revealed innovative forecasting approaches, indicating new, promising fields of research and applications. We anticipate even greater leaps in the upcoming M5, which we are delighted to be once again co-organizing, with UNIC at the helm”.

The excitement is building for the upcoming M Competition, among both the forecasting community and its major proponents. Along with the many innovations, there will be substantial monetary prizes, totaling $100,000, with global tech giants Google, Walmart, and Uber, as well as the International Institute of Forecasters (IIF), financially backing this year’s competition.

Addison Howard, Business Development Manager at Kaggle, underlined the platform’s central role in the M5: “We are excited to be the official home of this year’s Makridakis Competition. Forecasting challenges are not only important to furthering data science research, but they always bring a lot of excitement and participation. We’re anticipating a huge turnout from the Kaggle community!” On her part, IIF President, Gloria Gonzalez-Rivera, emphasized the Institute’s ongoing engagement with initiatives such as the M Competitions: “IIF strongly supports such efforts from leading researchers in forecasting competitions. We are very proud to sponsor the winning student submission for the M5. Looking forward to the competition developing and to the presentations that will follow at ISF2020 in Rio”. Slawek Smyl, Staff Data Scientist at Uber, spoke in similar terms of their backing of the M5: “The Makridakis Competitions have been hugely influential on the field of Forecasting, guiding the development of new algorithms and forecasting libraries. Accurate forecasting is critical to Uber’s business and we’re excited to continue our support of this essential competition in the field”.

Commenting on the evolution of the M Competitions, which bear his name, Professor Makridakis remarked: “The M5 will be the biggest, most ambitious, and most influential of all M Forecasting Competitions, opening up new avenues for academic research, identifying high-caliber methods, and further guiding the practice of Forecasting with its findings and recommendations”. The MOFC Director stood especially on the caliber and influence of this year’s partners: “These inroads are made possible by our exceptional global partners, whom I thank for their trust and support in the M5. The M Competitions, which I started almost 40 years ago, will have truly reached the pinnacle of their reach and service to Forecasting with Google, Walmart, Kaggle, Uber, and IIF in our corner”.

Given the standing of M Competitions in the forecasting community, as well as the significant contributions these have delivered throughout the years, fundamentally changing the field, the M5 is indeed expected to be the largest international competition of its kind. In that vein, over the next 4 months, thousands of individuals and teams are anticipated to compete to identify the most accurate, statistical or machine-learning (or hybrid) method(s) for different types of situations requiring predictions and uncertainty estimates.

As previously, the forthcoming M Competition findings will be presented and analyzed in the framework of a follow-up M Conference, set to repeat in New York on 7 and 8 December 2020. In that same vein, and similar to the M4 Publication, the findings of the M5 Competition and the M5 Conference will be published in a special issue of the prestigious International Journal of Forecasting. According to Pierre Pinson, Editor-in-Chief of the Journal: “Forecasting is of the utmost importance to our societies and we need to continuously invest in pushing the boundaries of knowledge. Forecast competitions are an ideal frame to do so, leveraging the dynamic forecasting community. The M5 is continuing the tradition and successes of the M Competitions and I am looking forward to see it happen and to featuring dedicated papers on this in an upcoming special issue”.

For more information about the M5 Forecasting Competition, please contact the Makridakis Open Forecasting Center at  or visit mofc.unic.ac.cy/m5-competition/.

About MOFC
The Makridakis Open Forecasting Center (MOFC) at the University of Nicosia, founded by Professor Spyros Makridakis, is one of the leading academic forecasting centers in the world. More specifically, MOFC conducts cutting-edge research on Forecasting, assisting organizations make accurate predictions, estimate levels of uncertainty, and manage risk through training, research, technology development, and consulting. Ultimately, MOFC aims to expand the utilization and value of Forecasting among business firms. The Center also collaborates with and supports the pioneering Data Science Programmes (BSc and MSc) offered at the University of Nicosia, to provide students with the requisite forecasting tools and applications, as well as the opportunity to participate in and data from the M Competitions, markedly enhancing the practical side of their studies.

About M Competitions
The Makridakis (or M) Forecasting Competitions are the brainchild of Professor Spyros Makridakis, a pioneer in the field and one of the foundational figures of Forecasting. The revolutionary initiative began almost four decades ago, with M Competitions taking place in 1982, 1993, 2000 and 2018. The first three M Competitions were hosted at INSEAD, while the M4 was organized by the Institute For the Future (IFF) of the University of Nicosia, with the support of the Forecasting & Strategy Unit at the National Technical University of Athens (NTUA). M Competitions have substantially contributed to improving forecasting accuracy and the estimation of uncertainty, as well as informing practitioners on the most appropriate forecasting method to use for their specific needs.

The post Press release: Launch M5 Forecasting Competition appeared first on International Institute of Forecasters.

21st International Symposium on Inventories
24-28 August 2020
Radisson Blu Béke Hotel, Budapest, Hungary

Deadline for abstract submission: March 31, 2020

The International Society for Inventory Research (ISIR) organizes its 21st International Symposium on Inventories, the only scholarly forum in the world focusing directly on inventories. The professional objective of organizing this Symposium is to provide a forum for an international exchange of ideas on various aspects of inventories. Papers on macro- and microeconomics, econometrics, economic policy, business, management, operations management and operations research aspects of inventory problems and related fields (production, logistics, etc.) are also invited.

The main tracks of the program follow the renewed sections of ISIR and cover the below broad topics:

• Economics of Inventory and Production
• Analytics and Forecasting for Inventory Control
• Interfaces of Inventory with Transportation, Production, Finance and Marketing
• Inventory coordination in supply chains (includes multi-echelon)
• Spare Parts Management and Maintenance Optimization
• Sustainable Inventory Management (includes perishables)

Special session for 2020 – Machine learning for inventory management

Learn more about our society!

We hope to welcome you at the 21st International Symposium on Inventories!

Attila Chikán
Executive Vice President, ISIR
T&F: + 36 1 267 8740
www.isir.hu

The post International Symposium on Inventories, Call for papers appeared first on International Institute of Forecasters.

The post IJF Editorial: Pierre Pinson, Editor in Chief appeared first on International Institute of Forecasters.

Every two years, the International Journal of Forecasting awards a prize to the best paper on energy forecasting. The prize is generously funded by Professor Tao Hong. This year, we will award the prize to a paper published in the IJF during the period 2017-2018. The prize will be US$1000 plus an engraved plaque. The award committee is composed of James Mitchell, Rafał Weron and Pierre Pinson.

Nominations are invited from any reader of the IJF. Each person may nominate up to three papers, but you cannot nominate a paper that you have coauthored yourself. Papers coauthored by Tao Hong or one of the award committee are not eligible for the prize. All nominations are to be accompanied by a short statement (up to 200 words) from the nominator, explaining why the paper deserves an award.

You can see the relevant papers published in the period 2017-2018 on Google Scholar. Of course, a good paper does not always get noticed, so don’t let the citation count sway you too much in nominating what you consider to be the best IJF paper from this period.

Send nominations to Pierre Pinson, IJF Editor-in-Chief, by 20 May 2020.

For more information, visit the IIF-Tao Hong award site.

Past winners:

• 2015-2016 IIF Tao Hong Award: Pierre Gaillard, Yannig Goude and Raphael Nedellec (2016) Additive models and robust aggregation for GEFCom2014 probabilistic electric load and electricity price forecasting”. International Journal of Forecasting 32(3): 1038-1050.
• 2013-2014 IIF Tao Hong Award: Rafał Weron (2014) “Electricity price forecasting: A review of the state-of-the-art with a look into the future”, International Journal of Forecasting 30(4): 1030–1081.

The post IIF Tao Hong Award, energy forecasting appeared first on International Institute of Forecasters.

All the world’s human population is affected by the current pandemic of COVID-19, its potential impact on health, as well as related measures e.g. confinement and social distancing, which have an impact on our economies and communities. In this situation, all of us wish to help and contribute, in one way or the other. It has become clear that modelling and forecasting of the dynamics of the epidemic, its diffusion and the impact of various measures, is at the core of current decision-making for policy makers and other experts involved. Many of our colleague modellers and forecasters are involved in initiatives at both national and international levels to help with this crisis. More broadly, we see a strong interest, from both experts and non-experts in looking at numbers and trying to predict the number of new cases, deaths, spreading, economic consequences, etc. for this pandemic, through blog posts and postings on social medias.

The fact that models and forecasts are needed to respond to epidemics is certainly not new. However, in view of the current focus on the science and practice of forecasting in relation to epidemics, the team of editors of the International Journal of Forecasting (IJF) agreed on the fact that the journal should make a contribution by consolidating knowledge on modelling, nowcasting and forecasting for epidemics – obviously with an additional focus on the current COVID-19 situation. This special section will aim to describe the various approaches to look at this problem, e.g. covering the angles of epidemiology, network science, as well as statistical and machine learning. It will also concentrate on some of the specific challenges with such problems, for instance related to the data available and its accuracy, the problem of forecast verification with limited data and in a dynamic environment, the fact that forecasts are produced while also taking measures to affect the spreading of the epidemic, forecast uncertainty quantification and communication, etc. It may be complemented by other papers focusing on the economic implications and more generally on the interactions between epidemics and economic decisions. Various topics may be considered such as measuring and forecasting the impact of the COVID-19 crisis on the macroeconomy and financial markets, historical lessons from previous pandemics, the role of increasing uncertainties or economic policy responses.

The preparation of the special section will start with a series of invited blog posts, to appear over the coming days and weeks on the International Institute of Forecasters (IIF) website. These will describe the contents of invited contributions for that special section. Invited papers will be submitted and reviewed throughout the Summer and Fall 2020, and they will appear online as soon as they are accepted. Invited comments and opinion papers will be gathered by a number of leading figures in forecasting, decision-making uncertainty, risk management, economics and epidemiology. In parallel, the special section will be complemented by papers presented at the Virtual IIF Workshop on “Economic forecasting in times of COVID-19” organized by Prof. Laurent Ferrara and Prof. Xuguang Simon Sheng. See announcement at https://forecasters.org/wp-content/uploads/26th-IIF-virtual-workshop.pdf

For the IJF team of editors,

Prof. Pierre Pinson
Editor in Chief
International Journal of Forecasting

The post IJF special section: Epidemics and forecasting with focus on COVID-19 appeared first on International Institute of Forecasters.

[IJF special section: Epidemics and forecasting with focus on COVID-19]

Jennifer L. Castle, Jurgen A. Doornik and David F. Hendry

COVID-19 currently dominates the physical and economic well-being of individuals and societies globally. We have published real-time short-term forecasts for confirmed cases and deaths for many parts of the world on an almost daily basis from 20 March onwards on www.doornik.com/COVID-19. These have largely been reliable indicators of what can be expected to happen in the next week.

Models based on well-established theoretical understanding supported by available evidence are crucial to viable policy-making in observational-data disciplines like economics, other social sciences and epidemiology. Despite that, economics has witnessed a long history of relatively simple data-based devices `out-forecasting’ formal `structural’ models. This phenomenon occurs in other subjects.  The reason is that shifts in the distributions of variables from their past behaviour lead to systematic mis-forecasting in all models in the equilibrium-correction class. That class comprises most widely-used models, from regressions, scalar and vector autoregressions, through cointegrated systems, to volatility models like ARCH and GARCH.

Models of pandemics such as the present coronavirus face this problem of non-stationarity. Epidemiological models have a sound theoretical basis and a history of useful applications. Nevertheless, novel viruses may behave in different ways from what models assume, and policy reactions to early predictions of mass deaths (e.g., by mandatory lockdowns) can shift distributions suddenly in ways that can be difficult to model formally. Added to their slow starts, then exponential increases gradually slowing, pandemic data are highly non-stationary. Indeed, the methodologies used for reporting the pandemic data are also non-stationary, with stochastic trends, such as the ramping up of testing, and distributional shifts, such as the sudden inclusion of care home cases. Thus, there is a compounding effect as the non-stationarity of the underlying data interacts with the non-stationarity of the reporting process.

Viable forecasting models must be able to handle this quadruple non-stationarity: two forms (stochastic trends and shifts) from two sources (outcomes and measurements thereof). Epidemiological models can be too highly driven by their assumptions, which combined with their assumed mathematical processes, can limit their usefulness in forecasting as they are not empirical enough. As a consequence, there is an important role in short-term forecasting after distributional shifts for adaptive data-based models using a class we call `robust’, namely devices that avoid systematic forecast failure after sudden distributional shifts. However, when forecasting that adaptability must remain firmly controlled to avoid excess volatility. An additional use of such models is that a noticeable drop in outcomes relative to baseline extrapolations can be an indication that policies are having a positive impact.

Our forecasts  are derived from such `robust’ models. Our aim was to provide short-term forecasts of the numbers of confirmed cases and of deaths attributed to COVID-19 as a guide to planning for the next few days, so that the next reported numbers would not be a surprise. The basis of these reported figures differs across countries and time: some countries just use hospital counts, some add in other locations like care homes, some do much more infection testing whereas others only record cases serious enough to need medical intervention. Occasionally, the basis is switched. Thus, our forecasts are of the next reports for the recording system then in use. Robustness after changes in the reporting basis is also an important attribute of our methods: the next forecast will obviously be incorrect, but updating the later forecasts will move them quickly back on track.

The methodology to construct the short-term forecasts involves several steps. The observed daily time series is first decomposed into a trend and a remainder. The trend is estimated by taking moving windows of the data and saturating these by linear trends. Selection from these trends is made by an econometric machine-learning algorithm, and the selected linear trends are then averaged to give the overall flexible trend. Next, the trend and remainder terms are forecast separately using the Cardt method and recombined in a final forecast. Cardt is an improved version of the method that we used in the M4 competition (International Journal of Forecasting, 2020). A second averaged forecast is also reported, where many forecast paths are averaged over because countries differ substantially in their degrees of variation.

The following graph, taken from www.doornik.com/COVID-19 on 2020-04-21 (slightly edited for clarity here), shows the number of deaths from COVID-19 for the World from our data sources listed in the paper (the thick grey line with dots). The estimated trend (blue dotted line) and forecasts (red solid line) with 80% confidence intervals are plotted, along with the average forecast up to three days back given in black. The teal line plots the scenario forecast for the World with forecast intervals, explained in the paragraph below. Further information and references can be found on our COVID-19 web site.

Estimates of the peak in daily counts are made from an averaged smoothed trend constructed for cumulative counts while creating the many forecasts. To allow for a genuine slowdown in new cases and deaths, we create four scenarios based on the Chinese experience earlier in the year. Automatic model selection is then used to select the closest scenario mix from a flexible lag length, so initial models have more variables than observations. These scenario forecasts are introduced when a slowdown is detected in order to have sufficient data on the paths to select the scenarios. We expect the scenario forecasts to become more reliable the further along a country is in recovery. This approach allows us to introduce stylized facts from the Chinese experience. The empirical distribution of daily confirmed counts earlier this year in China was highly skewed, with about 2/3 of the mass beyond the peak. Daily deaths were less skewed, but closer to a straight trend up, followed by a straight trend down.

A table on the webpage records information about the peak increase in the estimated trend for deaths, including when it occurred and the number of days elapsed since the peak. A growing number of countries entering that table provides hope that the dramatic economic costs of major lockdowns have been worthwhile, and could start ending.

The webpage also provides an initial visual evaluation of our forecasts. The following graph considers confirmed cases for the US, taken from www.doornik.com/COVID-19 on 2020-04-21. Observed values are given by the thick grey line with dots. The solid red and black lines are the out-of-sample forecasts and average forecasts that were made (for the former with confidence bands). In this case, the forecasts have given good indications of what was about to happen in the next week, although going up too steeply for the last few observations.

Initial comparisons with the https://mrc-ide.github.io/covid19-short-term-forecasts/index.html suggest that one week ahead our forecasts are unbiased and more accurate. Hence, we believe that flexible and robust time-series methods for forecasting do have a role in the current pandemic.

The post Short-term Forecasting of the Coronavirus Pandemic appeared first on International Institute of Forecasters.

[IJF special section: Epidemics and forecasting with focus on COVID-19]

Antonio García-Ferrer, Universidad Autónoma de Madrid

This is a summary of a set of weekly reports (that I have been writing since 3/25/2020) about measuring and forecasting the effects of COVID-19 in Spain, one of the countries where such effects are being more pernicious. For comparative purposes, I will also analyse the data of China (Hubei) and Italy as references. In the three cases, my daily database is the one published by the Coronavirus Resource Center of the John Hopkins University.

I will focus on three variables:  the number of confirmed contagions (CON), the number of deaths associated to the illness (DTH), and the number of people recovered from it (REC). The starting dates of the time series for each country are different. Chinese data start on 1/22/20, Italian data begins on 2/7/20, and the first Spanish data appeared on the 2/26/20. Consequently, Chinese series have 16 data points more than Italian series (actually, 29 more data points since Italian data shows the same figure 3 during the first 13 days), and 34 data points more than the Spanish series. At this stage, these sample differences are crucial to understand the basic discrepancies among the three countries. By the time of my first report (3/25/20) the situation seemed to be under control for China, while Italy and Spain were starting their individual nightmares, as Figure 1 attests. While Hubei clearly followed a logistic model, Italy and Spain seem to follow an exponential pattern, whose simple long-run extrapolation would lead to a general contagion of the whole population. However, as epidemiologists very well know, at the initial stages of growth both curves are similar only to drift away considerably after reaching the inflection point, as we observe in the Chinese case. Regarding other countries at the same time, we also observed three areas (Japan, Hong-Kong and Singapore) that reacted very quickly to the burst of epidemics, another successful country like South Korea, and a large set of countries following (with different delays) the path initiated by China.

The first question raised by most researchers since the early days of the pandemic is the quality of the data in terms of representativeness and reliability.  In the case of Spain at least, it is obvious that the number of cases reported is considerably lower than the real ones (that remain unknown). If only by personal experience, I know no less than 80 cases that do no to show up in the official statistics. This global phenomenon has been analysed by many scientific publications, trying to extrapolate from observed to real cases. With some discrepancies, the multiplication factor ranges from 7 to 10.  In the Spanish case, this amounts to a range between 700.000 to 1 million cases by the end of March.  Still, notably inferior to the 7 million figure that Imperial College reported about the same date (https://www.imperial.ac.uk/mrc-global-infectious-disease-analysis/covid-19/report-13-europe-npi-impact/).

As regards reliability, questions and bones of contentions are open issues. For example, at the beginning, public opinion showed doubts regarding the low values of death cases in Germany as a ratio of its confirmed cases. Many suggest that German authorities did not consider deaths related to COVID-19 if deaths were associated to previous serious pathologies. Others claim that the good results are the consequence of more than 1 million weekly PCR tests throughout the whole period. These are open questions, which will surely be analysed by exhaustive epidemiological studies in the future. For the moment, I will consider our database as a possible random sample of the true unobserved data. However, Chinese data show certain anomalies that are difficult to explain. In particular, its daily growth rate of CON, which was oscillating between 15-18% by 2/14/2020, suddenly dropped to 3% the next day, remained at this level the following four days and, dropped again to 0.5% on the fifth day. Finally, its growth rate reached zero the following week. Certainly, this experience is unique because no other country has followed a similar path and raises serious concerns about the reliability of its data (https://www.aei.org/research-products/report/estimating-the-true-number-of-chinas-covid-19-cases/).

Analysis of the data

What evidence was available to infer that the Chinese experience shall be repeated in the cases of Italy and Spain? If so, can we anticipate the dates of possible inflection points in both countries? Given the nonstationarity of the original series, I will focus on the daily growth rates that give us the pandemic’s propagation speed. Their main statistical indicators (mean, median and standard deviation) are not very useful if we use the whole sample. Large differences between mean and median results; and in many cases, standard deviations are considerably larger than means. This is why I have aggregated data in weeks where the evaluation of the main statistical indicators is more meaningful. Even so, estimated means and medians are radically different, and standard errors are very high during the first weeks. These results confirm the presence of high volatility, particularly for the Italian and Spanish cases. However, as we approach recent data, processes become more stable; means and medians are similar and standard deviations become much smaller.

The weekly observations provided the following evidences:

• On week 5, we observe the first Italian data (not very reliable). At the same time, Chinese data shows a huge drop from 10.8% of the previous week to a very low 1.4% rate. It is very likely that the inflection point in the Chinese case take place on this fifth week.
• On week 6, we observe the first incomplete Spanish data (without information on DTH and REC) as well as reliable Italian data. The daily mean growth rates for Italy are very high for CON and DTH (40% and 50%, respectively) and even higher for Spain (56%)
• The last three weeks confirm the end of the pandemic for Hubei. On the other hand, while we can see decreasing trends in Italian and Spanish variables, daily growth rate is still very high, 15% for Italy and 22% for Spain, in the case of CON, and even higher values for DTH.
• Watching carefully Spanish and Italian data during the last three weeks, we can see (in spite of the short length of the series) a week lag between Spanish and Italian data. In other words, we were replicating what was happening in Italy a week earlier. Let us see if this visual leading behaviour could be used to predict Spanish outcomes using Italian variables as leading indicators.

Methodology and forecasting results

Using the information provided by the Italian data, I shall use a very simple transfer function (TF) model based on both the lags of the Spanish outputs as well as the dynamic structure of the corresponding Italian inputs. The model is estimated in levels, so it is nonstationary with limited applicability for long-run forecasts. The statistical fitting (as measured by the residual sum of squares) is also very good. I proceed as follows:

• I estimate individual models for CON, DTH and REC using data from 2/26 to 3/20 and obtain 1, 2,….5 steps ahead forecasts until March 25^th.
• I repeat the same exercise including five additional observations, so my sample now ends at 3/25 and my forecast period ends at March 30^th.
• I keep repeating this procedure five more times until the last string of forecasts ending on April 24th. After this date, new forecasts are difficult to evaluate due to continuous changes on the database.

Results for CON and DTH are included in Figures 2 and 3. Forecasts are very precise for all forecasting periods and, only during the last forecasting horizon we observe a slight over-prediction in the case of DTH. Forecasts for REC (not included in this post) are also available, as well as the related prediction intervals.

Preliminary forecasting results using this methodology are very promising, in terms of both accurate daily forecasts and narrow prediction intervals. Two natural extensions of this procedure seem worth trying:  i) applying the same theoretical setting to more disaggregated data at regional level, and ii) using Spanish and/or Italian data as leading indicators for other countries like France, USA or the UK that started their pandemic episodes later.

The post Forecasting COVID-19 daily outcomes with simple transfer function models appeared first on International Institute of Forecasters.

The IIF holds an election every March for new Directors, replacing those whose term has expired. We are delighted to announce the new Directors elected to the IIF Board:

• Anastasios Panagiotelis, Monash University
• Shouyang Wang, University of Chinese Academy of Sciences
• Doris Wu, Sun Yat-sen University

We are also pleased to announce the new President, George Athanasopoulos, and to give a special and sincere thank you to the outgoing President, Gloria González-Rivera. We also send a special thank-you to our departing directors, Nuno Crato, Laurent Ferrara, Mohsen Hamoudia, and Reinaldo Souza. Their contributions over the years have been greatly appreciated.

We would like to thank all of the nominees who stood for election: Fernando Cyrino, PUC Rio; Jim Hoover, University of Florida; Malte Knueppel, Bundesbank, Germany; Tommaso Proietti, Universita di Roma “Tor Vergata”; Bahman Rostami-Tabar, Cardiff University. We encourage participation in elections each year. If you are interested in learning more about becoming a board member, please contact us.

Click here to learn more about our Board of Directors.

The post IIF Elections, 2020 – Directors Announced appeared first on International Institute of Forecasters.