A Deep Learning Based Illegal Insider Trading Detection And Prediction Technique In Stock Market Save
Illegal insider trading of stocks is based on releasing non-public information (e.g., new product launch, quarterly financial report, acquisition or merger plan) before the information is made public. Detecting illegal insider trading is difficult due to the complex, nonlinear, and non-stationary nature of the stock market. In this work, we present an approach that detects and predicts illegal insider trading proactively from large heterogeneous sources of structured and unstructured data using a deep-learning based approach combined with discrete signal processing on the time series data. In addition, we use a tree-based approach that visualizes events and actions to aid analysts in their understanding of large amounts of unstructured data. Using existing data, we have discovered that our approach has a good success rate in detecting illegal insider trading patterns. My research paper (IEEE Big Data 2018) on this can be found here: https://arxiv.org/pdf/1807.00939.pdf
#prediction folder contains the implementation of stock market volatility prediction using LSTM Neural Network. Keras is used as a wrapper with Tensorflow backend. #run cd prediction python run.python
#detection folder contains the implementation of anomalous time series detection using discrete signal processing. Matlab scripting language is used for the implementation. #run #open the script (deect_anomaly.m) with matlab and click the button run #from command line matlab -nodesktop -nosplash -r "detect_anomaly"
#litigation-classifier-and-visualizations folder contains code for huge amount of unstructered data (e.g., litigations) precessing, #classification and visualizations.
Open Source Agenda Badge
