Gated Ensemble of Spatio-temporal Mixture of Experts for Multi-task Learning in Ride-hailing System
This work provides an incremental improvement in spatio-temporal forecasting for ride-hailing companies by simultaneously predicting demand and supply-demand gaps across cities.
This paper addresses the challenge of simultaneously forecasting demand and supply-demand gaps in ride-hailing systems across multiple cities. The proposed GESME-Net architecture, which combines CRNN, CNN, and RNN with a task adaptation layer, outperformed single-task and multi-task deep learning benchmarks in both within-city and cross-city forecasting scenarios.
Ride-hailing system requires efficient management of dynamic demand and supply to ensure optimal service delivery, pricing strategies, and operational efficiency. Designing spatio-temporal forecasting models separately in a task-wise and city-wise manner to forecast demand and supply-demand gap in a ride-hailing system 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 these 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.