Abstract
The accurate prediction of online car-hailing demand plays an increasingly important role in real-time scheduling and dynamic pricing. Most studies have found that the demand of online car-hailing is highly correlated with both temporal and spatial distributions of journeys. However, the importance of temporal and spatial sequences is not distinguished in the context of seeking to improve prediction, when in actual fact different time series and space sequences have different impacts on the distribution of demand and supply for online car-hailing. In order to accurately predict the short-term demand of online car-hailing in different regions of a city, a combined attention-based LSTM (LSTM + Attention) model for forecasting was constructed by extracting temporal features, spatial features, and weather features. Significantly, an attention mechanism is used to distinguish the time series and space sequences of order data. The order data in Haikou city was collected as the training and testing datasets. Compared with other forecasting models (GBDT, BPNN, RNN, and single LSTM), the results show that the short-term demand forecasting model LSTM + Attention outperforms other models. The results verify that the proposed model can support advanced scheduling and dynamic pricing for online car-hailing.
Highlights
As an important component of the transport system, on-demand car-hailing and taxi services play increasingly important roles in reducing traffic carbon emissions and easing traffic congestion
The demand for online car-hailing shows a certain periodic change law according to time
The online car-hailing orders under different weather conditions have been analyzed to verify that weather characteristics have a certain impact on online car-hailing demand forecasts
Summary
As an important component of the transport system, on-demand car-hailing and taxi services play increasingly important roles in reducing traffic carbon emissions and easing traffic congestion. The accurate short-term demand forecasting of online car-hailing is one of the effective ways to enable the on-demand platform to understand the spatial and temporal distributions of passengers for enhancing the schedule of ride-hailing cars. It is helpful for increasing or decreasing the scale of online car-hailing to achieve a reasonable allocation and equilibrium of online car-hailing and passengers. In order to better predict the short-term demand for online car-hailing, an attention mechanism was introduced to determine the weights for temporal and spatial sequences. (2) Based on the historical data of large-scale online car-hailing, a short-term demand forecasting model of online car-hailing is developed, namely, LSTM + Attention.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have