Studying on Demand Prediction of Shared Bikes Considering Land-Use Information

In order to provide better service, shared bikes should be dynamically scheduled according to demand. Currently, research on demand prediction can be divided into two categories: traditional statistical models and deep learning models. The former aims at short-term prediction of 5–10 min, but scheduling cannot respond that quickly. The latter ignores influential factors, leading to a decline in accuracy and reliability. Therefore, this paper aims to develop a demand forecasting model that can significantly improve accuracy for long-term prediction with higher reliability. Taking the region within the inner ring of Pudong, Shanghai as the study area, an improved LSTM NN model is proposed, based on POI data which is represented land-use information. The improved model takes land-use information as a factor that influences demand of shared bikes. Improved LSTM NN demonstrates higher accuracy than both statistical models and the original LSTM NN, especially for long-term prediction.