A Data-Driven Model of a Firm's Operations With Application to Cash Flow Forecasting

Abstract

The cash flow from the operations of a firm is an endogenous function of the operational variables of the firm -- sales, operating cost, inventory, payables, receivables, etc. Cash flow depends on these variables, and in turn, these variables depend on cash flow and each other through the decisions made by the firm. Consequently, cash flow forecasting is a challenging problem. In this paper, we propose a generalizable and data-driven model of a firm's operations to disentangle this endogeneity and estimate causal impacts among variables. By estimating our model using quarterly public operational and financial data from S&P's Compustat database for 1990-2020, we obtain joint forecasts for cash flows and other operational variables as functions of their lagged values. We show that these joint forecasts are more accurate than those generated from univariate time-series models. Our model also helps quantify the short- and long-run impacts of structural shocks in variables on the entire system, which has applications in assessing the impact of exogenous macroeconomic factors such as recessions (or the COVID-19 pandemic) on future operational performance.