Join-based Social Ridesharing

Abstract

Social ridesharing becomes a promising and attractive solution to settle the trust and safety problems for current ridesharing service. In a typical social ridesharing, drivers and riders submit ride requests and ride offers to the service platform via their smart phones, respectively. Specifically, for each driver, the service platform provides a set of matching riders by taking into account trip similarities and social connections. A limitation of this approach is that they assume drivers arrive in the service platform in a stream fashion and the matching of driver and rider is processed in a snapshot model. To some extent, however, this approach may reduce the success rate of matching over the whole drivers and riders. In addressing this weakness, in this paper we propose a novel Join-based Ride Matching (JbRM) model where drivers’ ride offers and riders’ ride requests are processed in a join-based approach to achieve best utility over a time window. JbRM problem is indeed of practical usefulness, we design several efficient algorithms with a set of powerful pruning techniques to tackle this problem. Extensive experiments conducted on real-life datasets show that our proposed algorithms achieve desirable performance.