The rapid growth of ride-hailing platforms has created a highly competitive market where businesses struggle to make profits, necessitating better operational strategies. However, real-world experiments are risky and expensive for these platforms as they deal with millions of users daily. Thus, a need arises for a simulated environment where one can predict users' reactions to changes in the platform. Building such a simulation is challenging, as these platforms exist in dynamic environments where thousands of agents regularly interact with one another. This paper presents a framework to mimic and predict driver behaviors in ride-hailing services. We use a data-driven hybrid reinforcement learning and imitation learning approach for this. First, the agent utilizes behavioral cloning to mimic driver behavior from a real-world data-set. Next, reinforcement learning is applied to the pre-trained agents in a simulated environment, to allow them to adapt to changes in the platform. Our framework provides an ideal playground for ride-hailing platforms to experiment with platform-specific parameters such as trip fares and incentives to predict the drivers’ behavioral patterns.
Team Members - Tarindu Jayatilaka , Ravin Gunawardena
