Mining the Value Characteristics of One-Way Car-Sharing Users Based on Empirical Data

Abstract

Car-sharing has been emergent in many cities all over the world due to the environmental sustainability and the diverse service for users. However, the huge investment and the long payback period hinder the development of car-sharing. To this end, this study attempts to mine the value of car-sharing users in terms of empirical data, aiming to provide suggestions for companies to enhance user management. Based on the order data of a car-sharing company, several indicators are defined. On the basis, the users are divided into three categories, namely high-value users, low-value users and potential users. Furthermore, with the proposed indicators and the personal attributes, a prediction model is developed based on random forest method to predict the category of users in advance. The results show that with the observation period of 7 weeks, the long-term value type of a user can be predicted with accuracy of more than 80%.