Publications
Publications
- September 2010
- Management Science
Do Inventory and Gross Margin Data Improve Sales Forecasts for U.S. Public Retailers?
By: Saravanan Kesavan, Vishal Gaur and Ananth Raman
Abstract
Firm-level sales forecasts for retailers can be improved if we incorporate cost of goods sold, inventory, and gross margin (defined here as the ratio of sales to cost of goods sold) as three endogenous variables. We construct a simultaneous equations model, estimated using public financial and non-financial data, to provide joint forecasts of annual cost of goods sold, inventory, and gross margin for retailers using historical data. We show that sales forecasts from this model are more accurate than consensus forecasts from equity analysts. Further, the residuals from this model for one fiscal year are used to predict retailers for whom the relative advantage of model forecasts over consensus forecasts would be large in the next fiscal year. Our results show that historical inventory and gross margin contain information useful to forecast sales, and that equity analysts do not fully utilize this information in their sales forecasts.
Keywords
Sales; Forecasting and Prediction; Distribution; Goods and Commodities; Cost; Public Sector; Profit; Mathematical Methods; Analytics and Data Science; Retail Industry; United States
Citation
Kesavan, Saravanan, Vishal Gaur, and Ananth Raman. "Do Inventory and Gross Margin Data Improve Sales Forecasts for U.S. Public Retailers?" Management Science 56, no. 9 (September 2010): 1519–1533.