Scram

Abstract

Recommending routes for a group of competing taxi drivers is almost untouched in most route recommender systems. For this kind of problem, recommendation fairness and driving efficiency are two fundamental aspects. In the paper, we propose SCRAM, a sharing considered route assignment mechanism for fair taxi route recommendations. SCRAM aims to provide recommendation fairness for a group of competing taxi drivers, without sacrificing driving efficiency. By designing a concise route assignment mechanism, SCRAM achieves better recommendation fairness for competing taxis. By considering the sharing of road sections to avoid unnecessary competition, SCRAM is more efficient in terms of driving cost per customer (DCC). We test SCRAM based on a large number of historical taxi trajectories and validate the recommendation fairness and driving efficiency of SCRAM with extensive evaluations. Experimental results show that SCRAM achieves better recommendation fairness and higher driving efficiency than three compared approaches.

Adaptive passenger-finding recommendation system for taxi drivers with load balancing problem

“…On the other hand, in the second group, a route is defined as an exact path, i.e. a sequence of connected road segments (Ding et al, 2013;Dong et al, 2014;Qu et al, 2014;Qian et al, 2015;Lai et al, 2018). Following the detailed route, drivers expect to find a passenger along the way.…”

“…For both route types, two approaches were proposed for the route recommendation. The first is a two-stage approach (Ge et al, 2010;Hu et al, 2012;Ding et al, 2013;Dong et al, 2014;Qu et al, 2014;Qian et al, 2015;Lai et al, 2018;Luo et al, 2018;Qu et al, 2019). Firstly, the pick-up probabilities of hotspot or segment candidates are learned from historical data.…”

“…Moreover, multiple passenger-finding strategies can be used and recommending appropriate ones helps to improve drivers' performance. Two main strategies were used in the literature: waiting strategy (Hwang et al, 2015;Zhang et al, 2016;Kong et al, 2017;Wang et al, , 2018Huang et al, 2019) and hunting strategy (Ge et al, 2010;Hu et al, 2012;Luo et al, 2018;Qu et al, 2019;Ding et al, 2013;Dong et al, 2014;Qu et al, 2014;Qian et al, 2015;Lai et al, 2018); still, one strategy may be more effective than the other at a specific time and place. Increasing attention has been paid to combining the waiting and hunting strategies, called hybrid strategies Gao et al, 2018).…”

Minimizing Latency in Online Ride and Delivery Services

“…[25]), and to guarantee fairness within a group of competing drivers (cf. [24]). To address inefficiencies in taxi systems, several graph-based models and algorithms have been designed to minimize the total number of required taxis and to reduce the total idle time of taxi drivers (cf.…”