Cédric Poutré

About me

PhD graduate in financial mathematics under the supervision of professor Manuel Morales at University of Montreal. My thesis focused on financial econometrics and machine learning methods in high-frequency statistical arbitrage, and in limit order books anomaly detection. I'm a Fin-ML scholar, an IVADO scholar, and a Financial Market Surveillance Intelligence Centre scholar. You can find my thesis here: https://doi.org/1866/31935.

Outputs

Deep Unsupervised Anomaly Detection in High Frequency Markets

Inspired by recent advances in the deep learning literature, this article introduces a novel hybrid anomaly detection framework specifically designed for limit order book (LOB) data. A modified Transformer autoencoder architecture is proposed to learn rich temporal LOB subsequence representations, which eases the separability of normal and abnormal time series. A dissimilarity function is then learned in the representation space to characterize normal LOB behavior, enabling the detection of anomalous subsequences out-of-sample. We also develop a complete trade-based manipulation simulation methodology able to generate a variety of scenarios derived from actual trade-based fraud cases. The complete framework is tested on LOB data of five NASDAQ stocks in which we randomly insert synthetic quote stuffing, layering, and pump-and-dump manipulations. We show that the proposed asset-independent approach achieves new state-of-the-art fraud detection performance, without requiring any prior knowledge of manipulation patterns.\\ Article published in the Journal of Finance and Data Science: https://doi.org/10.1016/j.jfds.2024.100129