Financial Anomaly Detection for the Canadian Market

arXiv cs.LG / 4/6/2026

💬 OpinionSignals & Early TrendsIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper compares three anomaly-detection approaches—topological data analysis (TDA), PCA, and neural network-based methods—on Canadian market data (TSX-60).
It focuses on identifying major financial stress events, showing that TDA and neural network approaches outperform PCA.
Neural network methods such as GlocalKD and One-Shot GIN(E) are reported to deliver the strongest overall performance in detecting anomalies.
The authors argue that TDA’s success indicates that global topological features of the data carry meaningful signals for distinguishing financial stress periods.

Abstract

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.