Optimizing Two-Sided Promotion for Transportation Network Companies: A Structural Model with Conditional Bayesian Learning

The mobile app of a transportation network company (TNC) allows the TNC platform to run aggressive and diverse sales promotion to help introducing new product to two sides of users. This paper examines how two-sided sales promotion affects drivers’ willingness to use the TNC app and how the TNC forms its optimal promotion strategies accordingly. To investigate the effects of sales promotion, we estimate a structural model of drivers’ decisions of accepting orders and cancelling generated orders and their perception of passengers’ willingness to redeem sales promotion. Bayesian learning processes are introduced to account for decisions under uncertainty as the app is newly introduced. We find measurable evidence of taxi drivers’ learning about the attributes value of using transportation network app, indicating substantial value of promotion in early period since it not only encourages current usage, but also fosters learning that sustains drivers’ use afterwards. Our results also show that revealed tips from passengers signal low quality of orders, and platform cashback to passengers has positive effect on drivers by increasing drivers’ chances of being rewarded. Given the estimated parameters, we run simulations to explicitly measure indirect effects of sales promotion introduced by learning and show how cashback for passengers impacts the decisions of drivers. Finally, our experimental promotion policies show improved performance with regard to drivers’ willingness to use while being more cost effective.