Saved in:
Bibliographic Details
Main Authors: Miao, Yuyang, Xing, Huijun, Mandic, Danilo P., Constantinides, Tony G.
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.23619
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • 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.