Identification of Stock Market Manipulation with Deep Learning

Abstract

Anomaly detection is a common and critical data mining task, it seeks to identify observations that differ significantly from others. Anomalies may indicate rare but significant events that require action. Market manipulation is an activity that undermines stock markets worldwide. This paper shares five large real-world, labelled data sets of anomalous stock market data where market manipulation is alleged to have occurred. Cutting edge deep learning techniques are then shown to successfully detect the anomalous periods. An LSTM based method with dynamic thresholding is particularly promising in this domain as it was able to identify contextual local anomalies in the data quickly, taking seconds to score two years of trading data for each stock, which can often be a challenge for deep learning approaches.

A Survey on Stock Market Manipulation Detectors Using Artificial Intelligence

“…In any RNN, the network flow can be unidirectional as such the features flow from the input to the output, or it can be bidirectional as such the flow can be both forward and backward between the two layers. Tallboys et al [83] used a bidirectional LSTM to construct their LSTM-GAN architecture to detect stock manipulation cases. Data from five US companies were used to validate the proposed method, which has been vetted by US SEC as belonging to the manipulation cases.…”