Detecting and Predicting Evidences of Insider Trading in the Brazilian Market

Abstract

Insider trading is known to negatively impact market risk and is considered a crime in many countries. The rate of enforcement however varies greatly. In Brazil especially very few legal cases have been pursued and a dataset of previous cases is, to the best of our knowledge, nonexistent. In this work, we consider the Brazilian market and deal with two problems. Firstly we propose a methodology for creating a dataset of evidences of insider trading. This requires both identifying impactful news events and suspicious negotiations that preceded these events. Secondly, we use our dataset in an attempt to recognise suspicious negotiations before relevant events are disclosed. We believe this work can potentially help funds in reducing risk exposure (suspicious trades may indicate undisclosed impactful news events) and enforcement agencies in focusing limited investigation resources. We employed a Machine Learning approach based on features from both spot and options markets. In our computational experiments we show that our approach consistently outperforms random predictors, which were developed due to lack of other related works in literature.