I am an assistant professor at the Indian School of Business. My research builds on tools from economics, computer science, and statistics to develop data-driven solutions for problems in (i) Operations Management, and (ii) Marketplaces and Industrial Organization. I completed my Ph.D. from Cornell's S.C. Johnson School of Management under the supervision of Vishal Gaur.

I obtained B.Tech in Industrial and Production engineering from Indian Institute of Technology Delhi, M.Sc. in Management from INSEAD, and Masters in Management from Cornell University .


[1] A Data-Driven Model of a Firm's Operations With Application to Cash Flow Forecasting
     Kashish Arora and Vishal Gaur
     Under Review at Management Science
     Accepted at MSOM Supply-Chain SIG, 2022
     Accepted at the Wharton Workshop for Empirical Research, 2021

[Abstract] [SSRN]
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.

[2] Private vs. Pooled Transportation: Customer Preference and Design of Green Transport Policy
     Kashish Arora, Fanyin Zheng and Karan Girotra
     Under 2nd Round Review at Management Science
     Honorable Mention, POMS College of Sustainable Operations Best Paper Award, 2021
     1st Place, INFORMS Conference on Service Science Best Student Paper award, 2020
     Accepted at the Wharton EMPOM, 2020 & the Marketplace Innovation Workshop, 2021
     Invited for Presentation at Stanford GSB I.O. Seminar, 2021

[Abstract] [SSRN]
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.

[3] An Unsupervised Learning Framework for Improving Sales Forecasts
     Kashish Arora and Vishal Gaur
     Work in Progress

[4] Matching Supply and Demand for Renewable Energy: The Case of Smart Meters
     Kashish Arora
     Working paper, Preliminary draft available on request

Renewable sources in the next decade will meet a large proportion of the world's electricity demand. 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 other power sources) to match supply with demand.