Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.19893 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908673679294464 |
|---|---|
| author | Xu, Shuoyan Zhang, Yu Miller, Eric J. |
| author_facet | Xu, Shuoyan Zhang, Yu Miller, Eric J. |
| contents | Ride-hailing platforms are characterized by high-frequency, behavior-driven environments. Although survival analysis has been applied to recurrent events in other domains, its use in modeling ride-hailing driver behavior remains largely unexplored. This study formulates idle behavior as a recurrent survival process using large-scale platform data and proposes a Transformer-based framework that captures long-term temporal dependencies with causal masking and incorporates driver-specific embeddings to model latent heterogeneity. Results on Toronto ride-hailing data demonstrate that the proposed Frailty-Aware Cox Transformer (FACT) achieves the highest time-dependent C-indices and lowest Brier Scores, outperforming classical and deep learning survival models. This approach enables more accurate risk estimation, supports platform retention strategies, and provides policy-relevant insights. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_19893 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Frailty-Aware Transformer for Recurrent Survival Modeling of Driver Retention in Ride-Hailing Platforms Xu, Shuoyan Zhang, Yu Miller, Eric J. Machine Learning Ride-hailing platforms are characterized by high-frequency, behavior-driven environments. Although survival analysis has been applied to recurrent events in other domains, its use in modeling ride-hailing driver behavior remains largely unexplored. This study formulates idle behavior as a recurrent survival process using large-scale platform data and proposes a Transformer-based framework that captures long-term temporal dependencies with causal masking and incorporates driver-specific embeddings to model latent heterogeneity. Results on Toronto ride-hailing data demonstrate that the proposed Frailty-Aware Cox Transformer (FACT) achieves the highest time-dependent C-indices and lowest Brier Scores, outperforming classical and deep learning survival models. This approach enables more accurate risk estimation, supports platform retention strategies, and provides policy-relevant insights. |
| title | Frailty-Aware Transformer for Recurrent Survival Modeling of Driver Retention in Ride-Hailing Platforms |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2511.19893 |