Publication
Proper positioning of ride-sourcing drivers may improve vacant travel times, waiting times, and matching opportunities. Herein, we evaluate the potential repositioning response of drivers when provided a guidance based on estimates of their earnings in a system offering ride-hailing (solo) and ridesplitting (shared) rides. A continuous-time Markov chain forecasts individual drivers' near-future conditions to compute revenue estimates for a given repositioning decision (remain in the current area or move to a neighboring one). To ensure drivers receive earning estimates quickly, we propose an approximation to the revenue predictions based on steady-state conditions. We applied the proposed model in a simulation of the central business district of Shenzhen, China. Our main results show that repositioning could significantly decrease passenger abandonments in scenarios of significant demand imbalance and increase drivers' revenues. One must also highlight that the guidance may focus on results with more profitable rides, not necessarily with higher demand. Therefore, areas with low profitable requests can receive a poor service coverage.