Predicting Demand in a Three Sided Marketplace
Predicting Demand in a Three Sided Marketplace


In this talk we discuss the different demand forecasts we need to generate to optimize the interventions we make in the three-sided marketplace of on-demand food delivery. We go through different data preparation and modeling techniques for different prediction horizons and granularity. Further, we discuss some of the downstream secondary models which consume these forecasts to make optimal business decisions. Lastly we touch on how the Data Science team is organized at DoorDash to best execute on these problems.


As Head of Data Science and Machine Learning at DoorDash, Alok Gupta directs teams building models to optimize critical metrics necessary to balance a three-sided marketplace. With previous roles as Director of Data Science for both Lyft and Airbnb, Alok has abundant experience in using data science to make predictions at scale. Prior to this industry experience, Alok was a Research Fellow in Mathematics at Oxford University, earning his PhD in derivative pricing, work that he applied on Wall Street as a high frequency trader to predict movements in foreign exchange rates at high frequency.

Open Data Science




Open Data Science
One Broadway
Cambridge, MA 02142

Privacy Settings
We use cookies to enhance your experience while using our website. If you are using our Services via a browser you can restrict, block or remove cookies through your web browser settings. We also use content and scripts from third parties that may use tracking technologies. You can selectively provide your consent below to allow such third party embeds. For complete information about the cookies we use, data we collect and how we process them, please check our Privacy Policy
Consent to display content from - Youtube
Consent to display content from - Vimeo
Google Maps
Consent to display content from - Google