Scientific Forecasting

Using data science in order to solve a problem requires a scientific mindset more than coding skills. Data Science for Supply Chain Forecasting, Second Edition contends that a true scientific method which includes experimentation, observation, and constant questioning must be applied to supply chains to achieve excellence in demand forecasting. This second edition adds more than 45 percent extra content with four new chapters including an introduction to neural networks and the forecast value added framework. Part I focuses on statistical "traditional" models, Part II, on machine learning, and the all-new Part III discusses demand forecasting process management. The various chapters focus on both forecast models and new concepts such as metrics, underfitting, overfitting, outliers, feature optimization, and external demand drivers. The book is replete with do-it-yourself sections with implementations provided in Python (and Excel for the statistical models) to show the readers how to apply these models themselves. This hands-on book, covering the entire range of forecasting—from the basics all the way to leading-edge models—will benefit supply chain practitioners, forecasters, and analysts looking to go the extra mile with demand forecasting. Events around the book Link to a De Gruyter Online Event in which the author Nicolas Vandeput together with Stefan de Kok, supply chain innovator and CEO of Wahupa; Spyros Makridakis, professor at the University of Nicosia and director of the Institute For the Future (IFF); and Edouard Thieuleux, founder of AbcSupplyChain, discuss the general issues and challenges of demand forecasting and provide insights into best practices (process, models) and discussing how data science and machine learning impact those forecasts. The event will be moderated by Michael Gilliland, marketing manager for SAS forecasting software: https://youtu.be/1rXjXcabW2s

Forecasting is required in many situations. Stocking an inventory may require forecasts of demand months in advance. Telecommunication routing requires traffic forecasts a few minutes ahead. Whatever the circumstances or time horizons involved, forecasting is an important aid in effective and efficient planning. This textbook provides a comprehensive introduction to forecasting methods and presents enough information about each method for readers to use them sensibly.

Flood Forecasting: A Global Perspective describes flood forecast systems and operations as they currently exist at national and regional centers around the globe, focusing on the technical aspects of flood forecast systems. This book includes the details of data flow, what data is used, quality control, the hydrologic and hydraulic models used, and the unique problems of each country or system, such as glacial dam failures, ice jams, sparse data, and ephemeral streams and rivers. Each chapter describes the system, including details about its strengths and weaknesses, and covers lessons learned. This helpful resource facilitates sharing knowledge that will lead to improvements of existing systems and provides a valuable reference to those wishing to develop new forecast systems by drawing on best practices. Covers global systems allowing readers to see a worldwide perspective with different approaches used by existing flood forecast systems Provides historical coverage allowing readers to understand why forecast systems have developed as they have and to see how specific systems have dealt with common problems encountered Presents a vision of what appears to be the future of hydrologic forecasting and difficulties facing hydrologic forecasting Provides a helpful resource to facilitate improvements to existing systems based on a best practices approach

Social and natural scientists often are called upon to produce, or participate, in the pro duction of forecasts. This volume assembles essays that (a) describe the organizational and political context of applied forecasting, (b) review the state-of-the-art for many fore casting models and methods, and (c) discuss issues of predictability, the implications of forecaSt errors, and model construction, linkage and verification. The essays should be of particular interest to social and natural scientists concerned with forecasting large-scale systems. This project had its origins in discussions of social forecasts and forecasting method ologies initiated a few years ago by several social and natural science members of the Social Science Research Council's Committee on Social Indicators. It became appar ent in these discussions that certain similar problems were confronted in forecasting large-scale systems-be they social or natural. In response, the Committee hypothesized that much could be learned through more extended and systematic interchanges among social and natural scientists focusing on the formal methodologies applied in forecasting. To put this conjecture to the test, the Committee sponsored a conference at the National Center for Atmospheric Research in Boulder, Colorado, on June 10-13, 1984, on forecasting in the social and natural sciences. The conference was co-chaired by Committee members Kenneth C. Land and Stephen H. Schneider representing, respectively, the social and natural science mem bership of the Committee. Support for the conference was provided by a grant to the Council from the Division of Social and Economic Science of the National Science Foundation.

Extreme Weather Forecasting reviews current knowledge about extreme weather events, including key elements and less well-known variables to accurately forecast them. The book covers multiple temporal scales as well as components of current weather forecasting systems. Sections cover case studies on successful forecasting as well as the impacts of extreme weather predictability, presenting a comprehensive and model agnostic review of best practices for atmospheric scientists and others who utilize extreme weather forecasts. Reviews recent developments in numerical prediction for better forecasting of extreme weather events Covers causes and mechanisms of high impact extreme events and how to account for these variables when forecasting Includes numerous case studies on successful forecasting, outlining why they worked

NEW YORK TIMES BESTSELLER • NAMED ONE OF THE BEST BOOKS OF THE YEAR BY THE ECONOMIST “The most important book on decision making since Daniel Kahneman's Thinking, Fast and Slow.”—Jason Zweig, The Wall Street Journal Everyone would benefit from seeing further into the future, whether buying stocks, crafting policy, launching a new product, or simply planning the week’s meals. Unfortunately, people tend to be terrible forecasters. As Wharton professor Philip Tetlock showed in a landmark 2005 study, even experts’ predictions are only slightly better than chance. However, an important and underreported conclusion of that study was that some experts do have real foresight, and Tetlock has spent the past decade trying to figure out why. What makes some people so good? And can this talent be taught? In Superforecasting, Tetlock and coauthor Dan Gardner offer a masterwork on prediction, drawing on decades of research and the results of a massive, government-funded forecasting tournament. The Good Judgment Project involves tens of thousands of ordinary people—including a Brooklyn filmmaker, a retired pipe installer, and a former ballroom dancer—who set out to forecast global events. Some of the volunteers have turned out to be astonishingly good. They’ve beaten other benchmarks, competitors, and prediction markets. They’ve even beaten the collective judgment of intelligence analysts with access to classified information. They are "superforecasters." In this groundbreaking and accessible book, Tetlock and Gardner show us how we can learn from this elite group. Weaving together stories of forecasting successes (the raid on Osama bin Laden’s compound) and failures (the Bay of Pigs) and interviews with a range of high-level decision makers, from David Petraeus to Robert Rubin, they show that good forecasting doesn’t require powerful computers or arcane methods. It involves gathering evidence from a variety of sources, thinking probabilistically, working in teams, keeping score, and being willing to admit error and change course. Superforecasting offers the first demonstrably effective way to improve our ability to predict the future—whether in business, finance, politics, international affairs, or daily life—and is destined to become a modern classic.