Kashish Arora

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.

Large cities around the globe are facing an alarming growth in traffic congestion, to which a significant contributor are the private cabs operated by ride-hailing platforms. Pooled transportation options such as shuttle services are cheaper and greener alternatives but are still new to many customers and policy makers. In this work, we build a structural model to study customers’ preferences on prices and service features when choosing between private taxis and a scheduled shuttle service. Using the estimated model, we evaluate the efficacy of congestion surcharge policies in reducing congestion on the road. We find that a 20% congestion surcharge leads to 4% of customers switching from the cab to the shuttle service. We show that providing a 20% discount on shuttle rides achieves one-fourth of this effehe effect comes from new users of the shuttle service, our finding highlights the importance of incorporating customer preference heterogeneity in designing effective policies to manage congestion.

A large proportion of world's electricity demand is going to be met by renewable sources in the next decade. This poses a huge operational challenge: balancing the highly variable renewable electricity supply and the (relatively more) static demand. Using data from a large scale experiment in London, we examine the effect of dynamic prices (pushed through smart meters) on the response of consumers' demand. We build a consumer-level structural model of pricing and electricity consumption. Using the resultant estimates, we evaluate the efficacy of various policies (e.g., different tariff schemes and capacity allocations across different power sources) in terms of matching supply with demand.