Frailty-Aware Transformer for Recurrent Survival Modeling of Driver Retention in Ride-Hailing Platforms

TL;DR

This paper introduces a Transformer-based model called FACT that effectively predicts driver retention in ride-hailing platforms by modeling recurrent idle behavior as a survival process, outperforming existing methods.

Contribution

It presents a novel frailty-aware Transformer framework that captures long-term dependencies and driver heterogeneity for recurrent survival analysis in ride-hailing.

Findings

FACT achieves higher time-dependent C-indices.

FACT has lower Brier Scores.

Model improves risk estimation accuracy.

Abstract

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.