
Research Article
Construction and Evaluation of a Return Prediction Model for One-Way Car Sharing
@INPROCEEDINGS{10.1007/978-3-031-31891-7_5, author={Ryota Saze and Manato Fujimoto and Hirohiko Suwa and Keiichi Yasumoto}, title={Construction and Evaluation of a Return Prediction Model for One-Way Car Sharing}, proceedings={Mobile Computing, Applications, and Services. 13th EAI International Conference, MobiCASE 2022, Messina, Italy, November 17-18, 2022, Proceedings}, proceedings_a={MOBICASE}, year={2023}, month={4}, keywords={Electric Car Sharing Machine Learning Return Prediction Vehicle Uneven Distribution Problem}, doi={10.1007/978-3-031-31891-7_5} }
- Ryota Saze
Manato Fujimoto
Hirohiko Suwa
Keiichi Yasumoto
Year: 2023
Construction and Evaluation of a Return Prediction Model for One-Way Car Sharing
MOBICASE
Springer
DOI: 10.1007/978-3-031-31891-7_5
Abstract
One-way ECS (Electric Car Sharing Service) is attracting attention as a new sustainable mobility option in urban areas. On the other hand, the vehicle uneven distribution problem occurs in one-way ECSs due to their usage patterns. In this paper, we propose a vehicle return prediction model for vehicle relocation to solve this problem. In the proposed method, two machine learning models are created to predict where and when a user will return a vehicle using static information such as departure time and location, and dynamic information such as the vehicle’s current location and direction of movement. The model is used to continually update the prediction results of vehicle returns during use, aiming for more accurate predictions. The proposed method has been evaluated using actual data from a one-way ECS and has achieved an accuracy of 0.93 for the prediction of stations to be returned. The method also achieved a MAE of 42.3 min and MAPE of 47% for the prediction of return times.