Abstract :

Driver Attrition Has Emerged As A Critical Concern For Ride-hailing Platforms, As It Directly Influences Operational Efficiency, Service Continuity, And Customer Satisfaction. Identifying Drivers Who Are At High Risk Of Leaving The Organization At An Early Stage Enables Companies To Implement Targeted Retention Strategies And Maintain Workforce Stability. Conventional Approaches To Attrition Analysis Primarily Rely On Manual Surveys, Basic Statistical Techniques, And Rule-based Systems. However, These Methods Depend Heavily On Historical Insights And Human Judgment, Limiting Their Ability To Effectively Process Large-scale, High-dimensional Data And Uncover Complex, Hidden Relationships Among Influencing Factors. To Address These Limitations, The Proposed System Introduces A Hybrid Deep Learning And Machine Learning Framework For Accurate Driver Attrition Prediction. A Long Short-Term Memory (LSTM) Neural Network Is Employed To Learn And Extract Meaningful Latent Representations From Structured Driver Data, Capturing Intricate Feature Dependencies And Underlying Patterns. These Extracted Features Are Subsequently Utilized By A Greedy Tree (GT) Classifier To Perform The Final Classification, Ensuring Both Improved Predictive Performance And Model Interpretability. For Benchmarking Purposes, Traditional Machine Learning Models, Including Random Forest (RF), Gradient Boosting (GB), And Support Vector Classifier (SVC), Are Implemented And Evaluated. Experimental Results Demonstrate That The Proposed Greedy Long Short-Term Memory Tree (GLSTMT) Model Achieves Superior Performance, Attaining An Accuracy Of 100% On The Dataset Used In This Study. The Complete System Is Deployed Using A Flask-based Web Architecture, Facilitating Seamless Model Integration, Secure User Authentication, And Efficient Interaction Between Frontend And Backend Components.

Published:

09-4-2026

Issue:

Vol. 26 No. 4 (2026)

Page Nos:

2127-2137

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite