Proactive Rebalancing and Speed-Up Techniques for On-Demand High Capacity Ridesourcing Services

We present a probabilistic proactive rebalancing method and speed-up techniques for improving the performance of state-of-the-art real-time high-capacity fleet management framework. improve on both computational efficiency system performance. The include search-space pruning I/O cost reduction parallelization, reducing computation time by up to 97.67%, in experiments taxi trips New York City. routes idle vehicles future demands based estimates from historical demand, increasing service rate 4.8% average, decreasing waiting total delay 5.0% 10.7% respectively.