An Enhanced Ride Sharing Model Based on Human Characteristics and Machine Learning Recommender System

Abstract Ride Sharing provides benefits like reducing traffic and pollution, but currently, the usage is significantly low due to social barriers, long rider waiting time, and unfair pricing models. Considering the aforementioned issues, we present an Enhanced Ride Sharing Model (ERSM) in which riders are matched based on a specific set of human characteristics using Machine Learning. After trip completion, we record the user feedback and compute two main characteristics that are most important to riders. The registered and the computed characteristics are fed to a classification module, which later predicts the two main characteristics for new riders. We have carried an extensive simulation with Google Map APIs and real-time New York City Cab data to measure the model performance. Our proposed model and obtained results will help service providers to increase the usage of Ride Sharing, and implicitly preserve natural resources plus improve environmental conditions.