IE-OPIM Joint Graduate Seminar
  • FENS
  • IE-OPIM Joint Graduate Seminar

You are here


IE-OPIM Joint Graduate Seminar: Özden Gür Ali (Koç University)

 Multi-Period Ahead Forecasting with Residual Extrapolation and Information Sharing - Leveraging a Multitude of Retail Series

Date: Wednesday, December 9, 2015
Time: 13:40 – 14:30
Location: FENS G035

Abstract: Multiperiod sales forecasts are important inputs for operations at retail chains with hundreds of stores, and many different formats, customer segments and categories. In addition to the effects of seasonality, holidays and marketing, correlated random disturbances also affect sales across stores that share common characteristics. We propose a novel method, TwoStage Information Sharing that takes advantage of this challenging complexity. In this method, segmentspecific panel regressions with seasonality and marketing variables pool the data, in order to provide better parameter estimates. The residuals are then extrapolated nonparametrically using features that are constructed from the last twelve months of observations from the focal and related categorystore time series. The final forecast combines the extrapolated residuals with the forecasts from the first stage. Working with the extensive dataset of a retailer, we show that this method significantly outperforms both panel regression models (mixed model) with an AR (1) error structure and the autoregressive distributed lags (ADL) model, as well as the univariate exponential smoothing (Winters’) method. The further out the prediction, the greater the improvement.

Keywords: Multivariate time series, Sales forecasting, Panel data, Data mining, Regression, Retail, Multiperiod ahead forecast

Bio: Özden Gür Ali is an associate professor at the Koç University Business Administration Department. Her current research is in data mining in retail, banking and healthcare; particularly in forecasting with large multi-stream data and predicting customer behavior. She also works on pharmaceutical marketing and policy evaluation, in the US and Turkish systems. Özden teaches Big Data in Business and Public Sector, Management Science, Quantitative Methods in Business, Project Management, Forecasting, New Venture Development and Quality Management courses in BA and MBA programs. She also serves as the Associate Dean of College of Administrative Sciences and Economics department at Koç University. Prior to academia, Özden has ten years of global R&D and analytical management consulting experience with General Electric and ZS Associates, serving Fortune 100 companies in marketing, sales, productivity and quality. Özden holds a B.S. in Industrial Engineering from Boğaziçi University, and M.S. and Ph.D. degrees from Rensselaer Polytechnic Institute in Decision Sciences and Engineering Systems.