Financial Anomaly Detection for the Canadian Market

Luigi Caputi; Nicholas Meadows

q-fin.STApr 2, 2026

Financial Anomaly Detection for the Canadian Market

Authors: Luigi Caputi, Nicholas Meadows

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.

Figures & tables

Panel of Figure 1 — Figure 1: Pipeline of the Main Analysis

Panel of Figure 2 — Legend: 1-Start of Mortgage Crisis, 2-Peak of 2008 Crisis, 3-Greek Debt Crisis, 4- Taper Tanrum, 5 - Oil $<\$ 40 $, 6 - Oil$ <$20$ , 7- COVID19

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Panel of Figure 3 — Legend: 1 - Start of Mortgage Crisis, 2 - 2008 Financial Crisis , 3 - Flash Crash, 4 - Greek Debt Crisis, 5 - 2015 Stock Market Selloff, 6 - 2018 Stock Market Correction, 7 - COVID19

Anomaly Detection

Anomaly detection finds rare or unexpected patterns in data, from defective products and system faults to fraud and security threats.

See all 652 papers

An Interpretable Generative Framework for Anomaly Detection in High-Dimensional Financial Time Series
Mar 9, 2026Waldyn G MartinezTime-Series Anomaly Detection Interpretable Anomaly Detection
Department of Information Systems & Analytics Farmer School of Business Miami University Oxford, OH 45056
Extreme Volatility Warning under Label Scarcity via Multi-Source Anomaly Fusion
Jul 26, 2026Jin Qian, Zhangzhi Xiong, Mingrui Li +1Multimodal Anomaly Detection Semi-Supervised Anomaly Detection
ShanghaiTech University, Shanghai, China
Trivial Graph Features and Classical Learning are Enough to Detect Random Anomalies
Mar 2, 2026Matthieu Latapy, Stephany RajehAnomaly Detection Graph-Based Anomaly Detection
CNRS, LIP6 Sorbonne Universit´e Paris, France · Efrei Research Lab Efrei Paris Panth´eon-Assas Universit´e Villejuif, France

Mar 9, 2026J/K move · Enter open · S save

An Interpretable Generative Framework for Anomaly Detection in High-Dimensional Financial Time Series

Waldyn G Martinez

Department of Information Systems & Analytics Farmer School of Business Miami University Oxford, OH 45056

Time-Series Anomaly Detection Interpretable Anomaly Detection Unsupervised Anomaly Detection Financial Time Series Reconstruction-Based Anomaly Detection

Open paper AskPDF arXiv

Detecting structural instability and anomalies in high-dimensional financial time series is challenging due to complex temporal dependence and evolving cross-sectional structure. We propose ReGEN-TAD, an interpretable generative framework that integrates modern machine learning with econometric diagnostics for anomaly detection. The model combines joint forecasting and reconstruction within a refined convolutional--transformer architecture and aggregates complementary signals capturing predictive inconsistency, reconstruction degradation, latent distortion, and volatility shifts. Robust calibration yields a unified anomaly score without labeled data. Experiments on synthetic and financial panels demonstrate improved robustness to structured deviations while enabling economically coherent factor-level attribution.

Abstract

Anomaly Detection

Explore similar work

An Interpretable Generative Framework for Anomaly Detection in High-Dimensional Financial Time Series

Extreme Volatility Warning under Label Scarcity via Multi-Source Anomaly Fusion

Trivial Graph Features and Classical Learning are Enough to Detect Random Anomalies