Dimensionality reduction techniques to support insider trading detection

TL;DR

This paper introduces an unsupervised anomaly detection method using dimensionality reduction techniques like PCA and autoencoders to identify potential insider trading activities from trading data.

Contribution

It presents a novel reconstruction-based approach combining PCA and autoencoders for insider trading detection using only trading positions as input.

Findings

Effective identification of suspicious trading behaviors

Application to Italian stock market data around takeover bids

Supports market surveillance with unsupervised learning

Abstract

Identification of market abuse is an extremely complicated activity that requires the analysis of large and complex datasets. We propose an unsupervised machine learning method for contextual anomaly detection, which allows to support market surveillance aimed at identifying potential insider trading activities. This method lies in the reconstruction-based paradigm and employs principal component analysis and autoencoders as dimensionality reduction techniques. The only input of this method is the trading position of each investor active on the asset for which we have a price sensitive event (PSE). After determining reconstruction errors related to the trading profiles, several conditions are imposed in order to identify investors whose behavior could be suspicious of insider trading related to the PSE. As a case study, we apply our method to investor resolved data of Italian stocks around takeover bids.