EB-Boost: Medium-Long Term Forecasting Method of Supplies of Shared E-Cars in Smart Scenic Spots

Abstract

At present, shared e-cars have become an important part of traffic in scenic spots. While shared e-cars bring convenience to tourists, they also exert a certain influence on the management of the traffic environment in scenic spots. Nowadays, the threshold for shared e-cars is low, and all business operators occupy the market share of the scenic spots and put the shared-cars on the market without plans. This behavior takes up the limited space, exacerbating the congestion of scenic space. Therefore, predicting the amount of shared e-cars to be supplied by a scenic spot in the near future accurately is of great significance for major business entities to do resource scheduling, reduce operating costs, and create an open and coordinated traffic environment in smart scenic spots. However, the traditional time-series prediction models such as AutoRegressive and Moving Average Model, Holt-Winters, and Long ShortTerm Memory can only be used for short-term rough predictions, and cannot be available under some special circumstances such as holidays or rush hours. In our work, we proposed EB-Boost, an ensemble learning method using feature coding based on target. The EB-Boost studied from historical data such as weather data, timestamp data and business data and established probability model and learned relationship between features and targets. We used the data of shared e-cars operated by Roboy Technology company to build a model, and compared the prediction results of EB-Boost with traditional time-series algorithms and neural network algorithms. Finally, we also discuss the robustness of the model and the predictive effect of shared e-cars in other scenic spots.