Ride-hailing platforms have been facing the challenge of balancing demand and supply. Existing vehicle reposition techniques often treat drivers as homogeneous agents and relocate them deterministically, assuming compliance with the reposition. In this paper, we consider a more realistic and driver-centric scenario where drivers have unique cruising preferences and can decide whether to take the recommendation or not on their own. We propose i-Rebalance, a personalized vehicle reposition technique with deep reinforcement learning (DRL). i-Rebalance estimates drivers' decisions on accepting reposition recommendations through an on-field user study involving 99 real drivers. To optimize supply-demand balance and enhance preference satisfaction simultaneously, i-Rebalance has a sequential reposition strategy with dual DRL agents: Grid Agent to determine the reposition order of idle vehicles, and Vehicle Agent to provide personalized recommendations to each vehicle in the pre-defined order. This sequential learning strategy facilitates more effective policy training within a smaller action space compared to traditional joint-action methods. Evaluation of real-world trajectory data shows that i-Rebalance improves driver acceptance rate by 38.07% and total driver income by 9.97%.

Designing spatio-temporal forecasting models separately in a task-wise and city-wise manner poses a burden for the expanding transportation network companies. Therefore, a multi-task learning architecture is proposed in this study by developing gated ensemble of spatio-temporal mixture of experts network (GESME-Net) with convolutional recurrent neural network (CRNN), convolutional neural network (CNN), and recurrent neural network (RNN) for simultaneously forecasting spatio-temporal tasks in a city as well as across different cities. Furthermore, a task adaptation layer is integrated with the architecture for learning joint representation in multi-task learning and revealing the contribution of the input features utilized in prediction. The proposed architecture is tested with data from Didi Chuxing for: (i) simultaneously forecasting demand and supply-demand gap in Beijing, and (ii) simultaneously forecasting demand across Chengdu and Xian. In both scenarios, models from our proposed architecture outperformed the single-task and multi-task deep learning benchmarks and ensemble-based machine learning algorithms.

Mobile crowdsourcing has become easier thanks to the widespread of smartphones capable of seamlessly collecting and pushing the desired data to cloud services. However, the success of mobile crowdsourcing relies on balancing the supply and demand by first accurately forecasting spatially and temporally the supply-demand gap, and then providing efficient incentives to encourage participant movements to maintain the desired balance. In this paper, we propose Deep-Gap, a deep learning approach based on residual learning to predict the gap between mobile crowdsourced service supply and demand at a given time and space. The prediction can drive the incentive model to achieve a geographically balanced service coverage in order to avoid the case where some areas are over-supplied while other areas are under-supplied. This allows anticipating the supply-demand gap and redirecting crowdsourced service providers towards target areas. Deep-Gap relies on historical supply-demand time series data as well as available external data such as weather conditions and day type (e.g., weekday, weekend, holiday). First, we roll and encode the time series of supply-demand as images using the Gramian Angular Summation Field (GASF), Gramian Angular Difference Field (GADF) and the Recurrence Plot (REC). These images are then used to train deep Convolutional Neural Networks (CNN) to extract the low and high-level features and forecast the crowdsourced services gap. We conduct comprehensive comparative study by establishing two supply-demand gap forecasting scenarios: with and without external data. Compared to state-of-art approaches, Deep-Gap achieves the lowest forecasting errors in both scenarios.

Recently, the online car-hailing service, Didi, has emerged as a leader in the sharing economy. Used by passengers and drivers extensive, it becomes increasingly important for the car-hailing service providers to minimize the waiting time of passengers and optimize the vehicle utilization, thus to improve the overall user experience. Therefore, the supply-demand estimation is an indispensable ingredient of an efficient online car-hailing service. To improve the accuracy of the estimation results, we analyze the implicit relationships between the points of Interest (POI) and the supply-demand gap in this paper. The different categories of POIs have positive or negative effects on the estimation, we propose a POI selection scheme and incorporate it into XGBoost [1] to achieve more accurate estimation results. Our experiment demonstrates our method provides more accurate estimation results and more stable estimation results than the existing methods.