Capturing the Characteristics of Car-Sharing Users: Data-Driven Analysis and Prediction Based on Classification
This work explores the characteristics of the usage behaviour of station-based car-sharing users based on the actual operation data from a car-sharing company in Gansu, China. We analyse the characteristics of the users’ demands, such as usage frequency and order quantity, for a day with 24 1 h time...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2020-01-01
|
| Series: | Journal of Advanced Transportation |
| Online Access: | http://dx.doi.org/10.1155/2020/4680959 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850229585195565056 |
|---|---|
| author | Jun Bi Ru Zhi Dong-Fan Xie Xiao-Mei Zhao Jun Zhang |
| author_facet | Jun Bi Ru Zhi Dong-Fan Xie Xiao-Mei Zhao Jun Zhang |
| author_sort | Jun Bi |
| collection | DOAJ |
| description | This work explores the characteristics of the usage behaviour of station-based car-sharing users based on the actual operation data from a car-sharing company in Gansu, China. We analyse the characteristics of the users’ demands, such as usage frequency and order quantity, for a day with 24 1 h time intervals. Results show that most car-sharing users are young and middle-aged men with a low reuse rate. The distribution of users’ usage during weekdays shows noticeable morning and evening peaks. We define two attributes, namely, the latent ratio and persistence ratio, as classification indicators to understand the user diversity and heterogeneity thoroughly. We apply the k-means clustering algorithm to group the users into four categories, namely, lost, early loyal, late loyal, and motivated users. The usage characteristics of lost users, including maximum rental time and travel distance, minimum percentage of same pickup and return station, and low percentage of locals, have noticeable differences from those of the other users. Late loyal users have lower rental time and travel distance than those of the other users. This manifestation is in line with the short-term lease of shared cars to complete short- and medium-distance travel design concepts. We also propose a model that predicts the driver cluster based on the decision tree. Numerical tests indicate that the accuracy is 91.61% when the user category is predicted four months in advance using the observation-to-judgment period ratio of 3 : 1. The results in this study can support enterprises in user management. |
| format | Article |
| id | doaj-art-2b1d6fca8f7c43a88415047cfca65577 |
| institution | OA Journals |
| issn | 0197-6729 2042-3195 |
| language | English |
| publishDate | 2020-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Advanced Transportation |
| spelling | doaj-art-2b1d6fca8f7c43a88415047cfca655772025-08-20T02:04:10ZengWileyJournal of Advanced Transportation0197-67292042-31952020-01-01202010.1155/2020/46809594680959Capturing the Characteristics of Car-Sharing Users: Data-Driven Analysis and Prediction Based on ClassificationJun Bi0Ru Zhi1Dong-Fan Xie2Xiao-Mei Zhao3Jun Zhang4School of Traffic and Transportation, Beijing Jiaotong University, Beijing, ChinaSchool of Traffic and Transportation, Beijing Jiaotong University, Beijing, ChinaSchool of Traffic and Transportation, Beijing Jiaotong University, Beijing, ChinaSchool of Traffic and Transportation, Beijing Jiaotong University, Beijing, ChinaYunan Travelsky Airport Technology Co. Ltd., Yunnan, ChinaThis work explores the characteristics of the usage behaviour of station-based car-sharing users based on the actual operation data from a car-sharing company in Gansu, China. We analyse the characteristics of the users’ demands, such as usage frequency and order quantity, for a day with 24 1 h time intervals. Results show that most car-sharing users are young and middle-aged men with a low reuse rate. The distribution of users’ usage during weekdays shows noticeable morning and evening peaks. We define two attributes, namely, the latent ratio and persistence ratio, as classification indicators to understand the user diversity and heterogeneity thoroughly. We apply the k-means clustering algorithm to group the users into four categories, namely, lost, early loyal, late loyal, and motivated users. The usage characteristics of lost users, including maximum rental time and travel distance, minimum percentage of same pickup and return station, and low percentage of locals, have noticeable differences from those of the other users. Late loyal users have lower rental time and travel distance than those of the other users. This manifestation is in line with the short-term lease of shared cars to complete short- and medium-distance travel design concepts. We also propose a model that predicts the driver cluster based on the decision tree. Numerical tests indicate that the accuracy is 91.61% when the user category is predicted four months in advance using the observation-to-judgment period ratio of 3 : 1. The results in this study can support enterprises in user management.http://dx.doi.org/10.1155/2020/4680959 |
| spellingShingle | Jun Bi Ru Zhi Dong-Fan Xie Xiao-Mei Zhao Jun Zhang Capturing the Characteristics of Car-Sharing Users: Data-Driven Analysis and Prediction Based on Classification Journal of Advanced Transportation |
| title | Capturing the Characteristics of Car-Sharing Users: Data-Driven Analysis and Prediction Based on Classification |
| title_full | Capturing the Characteristics of Car-Sharing Users: Data-Driven Analysis and Prediction Based on Classification |
| title_fullStr | Capturing the Characteristics of Car-Sharing Users: Data-Driven Analysis and Prediction Based on Classification |
| title_full_unstemmed | Capturing the Characteristics of Car-Sharing Users: Data-Driven Analysis and Prediction Based on Classification |
| title_short | Capturing the Characteristics of Car-Sharing Users: Data-Driven Analysis and Prediction Based on Classification |
| title_sort | capturing the characteristics of car sharing users data driven analysis and prediction based on classification |
| url | http://dx.doi.org/10.1155/2020/4680959 |
| work_keys_str_mv | AT junbi capturingthecharacteristicsofcarsharingusersdatadrivenanalysisandpredictionbasedonclassification AT ruzhi capturingthecharacteristicsofcarsharingusersdatadrivenanalysisandpredictionbasedonclassification AT dongfanxie capturingthecharacteristicsofcarsharingusersdatadrivenanalysisandpredictionbasedonclassification AT xiaomeizhao capturingthecharacteristicsofcarsharingusersdatadrivenanalysisandpredictionbasedonclassification AT junzhang capturingthecharacteristicsofcarsharingusersdatadrivenanalysisandpredictionbasedonclassification |