Individualized Reservation fare optimization for Designated Driver Service

Ride-hailing services like Designated Driver Service (DDS) offer reservation options, allowing users to book rides at their desired times. To improve the convenience for reservation service customers and ensure the highest number of completed rides, it’s essential to maximize the number of available drivers for assignments. To reach this objective, we predict the conversion probability - the likelihood of customers proceeding after seeing the price - and the assignment probability, which is the likelihood of drivers accepting the reservation request. Based on these two probabilities, we aim to identify a pricing strategy that maximizes both probabilities and propose this price within the service. To accomplish this, we leverage the conversion and assignment probabilities to establish the expected actual ride count as the objective function. We optimize the pricing in the direction that maximizes this anticipated ride count, and the resultant optimal price is integrated into the reservation service. This study presents an innovative method employing Bayesian Optimization(BO) to establish a mutually advantageous pricing scheme for both customers and drivers. This contribution enhances the investigation into effective pricing strategies within the context of reservation-based vehicle dispatch services.