A Multi-Task Matrix Factorized Graph Neural Network for Co-Prediction of Zone-Based and OD-Based Ride-Hailing Demand

Abstract

Ride-hailing service has witnessed a dramatic growth over the past decade but meanwhile raised various challenging issues, one of which is how to provide a timely and accurate short-term prediction of supply and demand. While the predictions for zone-based demand have been extensively studied, much less efforts have been paid to the predictions for origindestination (OD) based demand (namely, demand originating from one zone to another). However, OD-based demand prediction is even more important and worth further explorations, since it provides more elaborate trip information in the near future as reference for fine-grained operations, such as the routing and matching of shared ride-hailing services that pick up and drop off two or more passengers in each ride. Simultaneous prediction of both zone-based and OD-based demand can be an interesting and practical problem for the ride-hailing platforms. To address the issue, we propose a multi-task matrix factorized graph neural network (MT-MF-GCN), which consists of two major components: (1) a GCN (graph convolutional network) basic module that captures the spatial correlations among zones via mixture-model graph convolutional (MGC) network, and (2) a matrix factorization module for multi-task predictions of zone-based and OD-based demand. By evaluations on the realworld on-demand data in Manhattan and Haikou, we show that the proposed model outperforms the state-of-the-art baseline methods in both zone-and OD-based predictions.

Graph Neural Networks for Intelligent Transportation Systems: A Survey

“…In another study, a multi-task matrix-factorized graph neural network model (MT-MF-GCN) has also been proposed by Feng et al [70] in order to predict both zone-based and OD-based demand simultaneously in ride-hailing services. Two major components make up the proposed model; the GCN basic module, which captures the spatial correlations among zones via a mixture-model graph convolutional network, and the matrix factorization module, which is utilized for multi-task predictions of zone-based and OD-based demand.…”

Dynamic Multi-View Coupled Graph Convolution Network for Urban Travel Demand Forecasting

“…Du et al [11] proposed a dynamically transformed convolutional neural network that uses graph convolution on a dynamically transformed network with the evolutionary flow. Feng et al [28] proposed a multi-task matrix factorization graph neural network to achieve joint prediction of inflow, outflow, and OD-based ridership demand within a single model framework.…”

Joint Demand Prediction for Multimodal Systems: A Multi-task Multi-relational Spatiotemporal Graph Neural Network Approach

“…Single-mode demand prediction is a well-studied problem. Early studies usually model travel demand as a time series based on various regression models, including ARIMA [9], local regression [10], Kalman Filter [11] and Bayesian Inference [12]. For instance, Moreira-Matias et al [13] developed an ensembled learning-based method for taxi demand prediction by combining ARIMA with time-varying Poisson models.…”

“…A multi-zone demand prediction model was presented in [25] using a convolutional multi-task learning network. Both Wang et al [7] and Feng et al [12] introduced a spatiotemporal architecture for co-prediction of zone-based and origin-destination-based demand values. In [26], the demand prediction for each zone is regarded as a distinct task, and an adaptive task grouping strategy was developed for community-aware multi-task demand prediction.…”