A Deep Learning Based Multi-Block Hybrid Model for Bike-Sharing Supply-Demand Prediction

Abstract

As a new type of short distance commuting, the station-free sharing bike effectively alleviates urban traffic congestion. Thus, they are deployed in a large scale in many cities. However, various complex factors, including spatial, temporal, and other external information, result in serious imbalance of supply and demand between regions, which makes accurate prediction a challenging issue. In this study, our primary objective is to accurately forecast supply and demand by leveraging multi-source datasets. Based on the visual analysis about spatial-temporal characteristics of GPS data in Shanghai, we presented the innovative methods of Area of Interest grading and Traffic Analysis Zone division of bike-sharing, and revealed the distribution characteristics of sharing bike trips. A multi-block hybrid model where three blocks were separately modeled according to different data types was proposed. Moreover, eight state-of-theart models and two variant models were developed as benchmarks to compare and evaluate the proposed model. The results suggested that MBH outperforms ten baselines with the highest accuracy. In addition, we conducted practical application of prediction results to validate that the proposed model could provide effective information for scheduling and rebalancing of bike-sharing system.

Forecasting usage and bike distribution of dockless bike‐sharing using journey data

“…Autoregression model is commonly used for forecasting univariate time series and VAR is a generalisation of the AR model for multiple time series and suitable for MIMO forecasting. (d) LSTM : It is a prominent RNN extension with forget gate, input gate, and output gate. LATM is widely used as the baseline of prediction [8, 17, 18, 24, 31]. This method can solve short‐term memory and vanishing gradient problem.…”

“…Wang et al [23] proposed low‐rank matrix completion to predict Mobike departure and arrival of grids in Beijing. Xu et al [24] established hybrid neural networks to forecast usage of 274 grids in Shanghai.…”

Bike sharing usage prediction with deep learning: a survey

“…Conflict of interest The authors declare that they have no conflict of interest. Weather [7,9,11,18,21,23,25,44,48,54,55,58,69,70,76,77,88,89] Calendar [11, 18, 21, 25, 44, 48, 54, 55, 58, 69-71, 76, 88, 89] PoI [9,25,48,71,76,77] Air Quality [9] Social Event [77] Land Usage [12] Public Transit Usage [12] Traffic Accident [45]…”

Short-Term Prediction of Bike-Sharing Demand Using Multi-Source Data: A Spatial-Temporal Graph Attentional LSTM Approach

“…Ai et al [30] proposed a Conv-LSTM model and predicted the dockless bike-sharing systems distribution within a short-run period by considering spatial-temporal variables. Xu et al [31] constructed a Multi-Block Hybrid model by involving CNN and GRU to implement short-run dockless bike-sharing prediction. Furthermore, Graph Neural Network (GCN) could detect the complex heterogeneous spatio-temporal effects of bike-sharing ridership, by treating the bike station as the vertices.…”