The Forecasting Seminar features education sessions on various forecasting approaches, detailing both how they work and how they are applied. Topics are presented using a combination of lecture and real-world examples drawn from a wide range of industries. The seminar is taught by Professor Len Tashman, Professor Emeritus at the University of Vermont (UVM). Len consistently receives rave reviews for his ability to relate forecasting concepts to business practitioners and has received numerous awards for excellence in teaching.

Note: for those attendees who don’t want to miss out on other sessions during the main conference but want to attend the Forecasting Seminar, the majority of the Forecasting Seminar is also offered as a pre-conference workshop. The pre-conference workshop covers all of the topics listed below with the exception of Box-Jenkins and Dynamic Regression.

Introduction to Business Forecasting
A broad overview of business forecasting and its role in the corporation. Topics include approaches to forecasting, features of data and selection of appropriate forecasting methods.

Forecast Accuracy and Evaluation
A detailed look into evaluating the accuracy of forecasting methods. Topics include a summary of findings from forecasting competitions and how to use out-of-sample testing as a predictor of model performance.

Exponential Smoothing Models
A survey of exponential smoothing techniques with particular emphasis on the Holt-Winters family of models. Topics include pros and cons of using these models, how and when they should be applied, how they work, parameter optimization and model diagnosis.

Event Models
Event models extend the functionality of exponential smoothing models by providing adjustments for promotions, strikes and other noncalendar based events. This session addresses how these models work, how and when they should be used and how to customize their design to best suit your needs.

Box-Jenkins
An exploration into the use of ARIMA models for business forecasting. Topics include advantages/disadvantages of using these models, how and when they should be applied, automatic identification procedures, differencing and model diagnostics.

Forecasting a Product Hierarchy
A discussion of issues pertaining to forecasting large volumes of data. Topics include evaluating and forecasting SKU data, ABC (Pareto) classification of data, measuring accuracy across multiple time series, and the role of forecasting in Demand/Supply Chain Management solutions. An extension of batch forecasting, this section explores hierarchical forecasting techniques. Lesson topics include discussion of the need for forecasting at various levels, product vs. geographical hierarchies, reconciliation strategies, top-down vs. bottom-up approaches, and adjustment for seasonality.

Dynamic Regression
A detailed look into the ins and outs of regression forecasting. Topics include determining when regression models are best applied, how to build the model, ordinary least squares, leading indicators, lagged variables, Cochrane-Orcutt models, hypothesis testing, and the use of "dummy" variables.

Business Forecast Systems in cooperation with the International Institute of Forecasters