Joint predictions of multi-modal ride-hailing demands: A deep multi-task multi-graph learning-based approach

• Published in: Transportation research. Part C, Emerging technologies Vol. 127; p. 103063
• Main Authors: Ke, Jintao, Feng, Siyuan, Zhu, Zheng, Yang, Hai, Ye, Jieping
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.06.2021
• Subjects: Deep multi-task learning; Demand prediction; Multi-graph convolutional network; Ride-hailing; Ride-hailing; Deep multi-task learning; Demand prediction; Multi-graph convolutional network
• ISSN: 0968-090X; 1879-2359
• DOI: 10.1016/j.trc.2021.103063

•We propose a multi-task multi-graph model to predict multi-ride-hailing demands.•Two methods, namely RCT and MLR, share knowledge for different prediction tasks.•We study the Manhattan dataset that contains both solo and shared rides.•The proposed model outperforms the state-of-art algorithms in prediction accuracy. Ride-hailing platforms generally provide various service options to customers, such as solo ride services, shared ride services, etc. It is generally expected that demands for different service modes are correlated, and the prediction of demand for one service mode can benefit from historical observations of demands for other service modes. Moreover, an accurate joint prediction of demands for multiple service modes can help the platforms better allocate and dispatch vehicle resources. Although there is a large stream of literature on ride-hailing demand predictions for one specific service mode, few efforts have been paid towards joint predictions of ride-hailing demands for multiple service modes. To address this issue, we propose a deep multi-task multi-graph learning approach, which combines two components: (1) multiple multi-graph convolutional (MGC) networks for predicting demands for different service modes, and (2) multi-task learning modules that enable knowledge sharing across multiple MGC networks. More specifically, two multi-task learning structures are established. The first one is the regularized cross-task learning, which builds cross-task connections among the inputs and outputs of multiple MGC networks. The second one is the multi-linear relationship learning, which imposes a prior tensor normal distribution on the weights of various MGC networks. Although there are no concrete bridges between different MGC networks, the weights of these networks are constrained by each other and subject to a common prior distribution. Evaluated with the for-hire-vehicle datasets in Manhattan, we show that our proposed approach outperforms the benchmark algorithms in prediction accuracy for different ride-hailing modes.