Forecasting Real Inventories and the Anomaly of Money Illusion
Combining Regression With A Neural Network Approach Shows Promising Results
By Anthony Joseph, Maurice Larrain, and Eshwar Singh
Anthony Joseph is an Associate Professor of Computer Science at Pace University. His primary research focus is on econometrics and applications of neural network technology to forecasting business cycle variables. His Ph.D. is fromthe City University of New York.
Maurice Larrain is an AssociateProfessor ofFinance atPaceUniversity.He began his forecasting career in a joint venturewithColumbiaUniversity’sCenter for International Business Cycle Research. His bachelor, masters and Ph.D. are all from Columbia University.
Eshwar Singh has spent eight years with the Bank of New York and is currently a senior support analyst in the Deposit Service Division. His research interests are applying neural networks to forecasting time series. He has a B.A. from Queens College and a M.Sc. from Pace University, both degrees in computer science.
While the transmission mechanism of inventory behavior in the business cycle has been studied, less effort has been devoted to applied forecasting of inventory change.Inventory fluctuations have accounted for a sizable portion of the changes in U.S. GDP during recessions over the past fifty years. In this paper, we report on out-of-sample forecasts of manufacturing and trade inventories generated by regression and neural network methodology. Our forecasting model is Metzlerian in approach, in that the divergence between actual and targeted sales is hypothesized as the primary cause of inventory imbalance. Our forecasts also rely on the slow adjustment of inventory investment to sales surprises. However, the likely presence of money illusion is a caveat to users, and we address several distortions it introduces to inventory management measures.
