This report presents a comprehensive analysis of an unsupervised multi-expert machine learning framework for detecting short ticketing fraud in railway systems. The study introduces an A/B/C/D station classification system that successfully identifies suspicious patterns across 30 high-risk stations. The framework employs four complementary algorithms: Isolation Forest, Local Outlier Factor, One-Class SVM, and Mahalanobis Distance. Key findings include the identification of five distinct short ticketing patterns and potential for short ticketing recovery in transportation systems.
@article{arxiv.2510.23619,
title = {Short Ticketing Detection Framework Analysis Report},
author = {Yuyang Miao and Huijun Xing and Danilo P. Mandic and Tony G. Constantinides},
journal= {arXiv preprint arXiv:2510.23619},
year = {2025}
}