Capturing the Characteristics of Car-Sharing Users: Data-Driven Analysis and Prediction Based on Classification
Bibliographic record
Abstract
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".