A machine learning approach to support decision in insider trading detection

TL;DR

This paper introduces two unsupervised machine learning methods to detect potential insider trading by analyzing trading patterns and group behaviors around price-sensitive events, demonstrated on Italian stock data.

Contribution

The paper presents novel unsupervised clustering techniques for identifying individual anomalies and coordinated groups indicative of insider trading activities.

Findings

Effective detection of trading anomalies near sensitive events.

Identification of coherent investor groups acting in concert.

Application to real Italian stock data demonstrates practical utility.

Abstract

Identifying market abuse activity from data on investors' trading activity is very challenging both for the data volume and for the low signal to noise ratio. Here we propose two complementary unsupervised machine learning methods to support market surveillance aimed at identifying potential insider trading activities. The first one uses clustering to identify, in the vicinity of a price sensitive event such as a takeover bid, discontinuities in the trading activity of an investor with respect to his/her own past trading history and on the present trading activity of his/her peers. The second unsupervised approach aims at identifying (small) groups of investors that act coherently around price sensitive events, pointing to potential insider rings, i.e. a group of synchronised traders displaying strong directional trading in rewarding position in a period before the price sensitive event. As a case study, we apply our methods to investor resolved data of Italian stocks around takeover bids.