Short-term FFBS demand prediction with multi-source data in a hybrid deep learning framework

The primary objective of this study is to predict the short-term demand of free-floating bike sharing (FFBS) using deep learning approach. The FFBS trip data in Shanghai city are collected from the Mobike Company. Other datasets such as weather data and air quality data are also collected. The spatiotemporal patterns of FFBS demand indicates that the weekday rides exhibit an obvious commuting pattern while the weekend rides are usually involved with various trip purposes. Then, a hybrid deep learning neural network (HDL-net) is developed to predict the short-term FFBS demand for different time intervals including 15, 20 and 30 min. The proposed HDL-net exhibits better performance on morning peak than the evening peak and non-peak hours for all the three time intervals. Moreover, five benchmark methods are also used to compare with the proposed HDL-net. The results suggest that the proposed hybrid deep learning framework outperform the benchmarks in the prediction performance for all three time intervals. The results of this study could provide insightful suggestions for transportation authorities to develop effective rebalancing strategies and bike lanes planning schemes to promote the service level of cycling in an urban city.