Do Inventory and Gross Margin Data Improve Sales Forecasts for U.S. Public Retailers?
研究了将销售成本、存货和毛利率作为内生变量构建联立方程模型，利用历史财务数据预测零售商年度销售，发现模型预测比分析师共识更准确，且历史存货和毛利率包含分析师未充分利用的预测信息。
Firm-level sales forecasts for retailers can be improved if we incorporate cost of goods sold, inventory, and gross margin (defined by us 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 nonfinancial 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.