In this work we evaluate the performance of three classes of methods for detecting financial anomalies: topological data analysis (TDA), principal component analyis (PCA), and Neural Network-based approaches. We apply these methods to the TSX-60 data to identify major financial stress events in the Canadian stock market. We show how neural network-based methods (such as GlocalKD and One-Shot GIN(E)) and TDA methods achieve the strongest performance. The effectiveness of TDA in detecting financial anomalies suggests that global topological properties are meaningful in distinguishing financial stress events.
@article{arxiv.2604.02549,
title = {Financial Anomaly Detection for the Canadian Market},
author = {Luigi Caputi and Nicholas Meadows},
journal= {arXiv preprint arXiv:2604.02549},
year = {2026}
}