Using Spatio-temporal Deep Learning for Forecasting Demand and Supply-demand Gap in Ride-hailing System with Anonymised Spatial Adjacency Information
This research provides improved forecasting accuracy for ride-hailing companies, helping to reduce passenger waiting times and driver search friction, which is an incremental improvement for the ride-hailing industry.
This paper addresses the challenge of forecasting spatio-temporal demand and supply-demand gaps in ride-hailing systems, especially when spatial adjacency information is anonymized. The proposed spatio-temporal deep learning architecture, integrating a feature importance layer with 1D CNN and IndRNN, outperforms conventional time-series and machine learning models on real-world Didi Chuxing datasets.
To reduce passenger waiting time and driver search friction, ride-hailing companies need to accurately forecast spatio-temporal demand and supply-demand gap. However, due to spatio-temporal dependencies pertaining to demand and supply-demand gap in a ride-hailing system, making accurate forecasts for both demand and supply-demand gap is a difficult task. Furthermore, due to confidentiality and privacy issues, ride-hailing data are sometimes released to the researchers by removing spatial adjacency information of the zones, which hinders the detection of spatio-temporal dependencies. To that end, a novel spatio-temporal deep learning architecture is proposed in this paper for forecasting demand and supply-demand gap in a ride-hailing system with anonymized spatial adjacency information, which integrates feature importance layer with a spatio-temporal deep learning architecture containing one-dimensional convolutional neural network (CNN) and zone-distributed independently recurrent neural network (IndRNN). The developed architecture is tested with real-world datasets of Didi Chuxing, which shows that our models based on the proposed architecture can outperform conventional time-series models (e.g., ARIMA) and machine learning models (e.g., gradient boosting machine, distributed random forest, generalized linear model, artificial neural network). Additionally, the feature importance layer provides an interpretation of the model by revealing the contribution of the input features utilized in prediction.