Machine Learning Applications
Process, analyze, and engineer features from large financial time series data sets, and create predictive financial time series models by training and validating machine learning algorithms. For general information on machine learning, see Machine Learning in MATLAB and Supervised Learning Workflow and Algorithms.
- Machine Learning for Statistical Arbitrage: Introduction
Get an overview of the workflow for statistical arbitrage and then follow a series of examples to see how capabilities in MATLAB® apply.
- Machine Learning for Statistical Arbitrage I: Data Management and Visualization
Apply techniques for managing, processing, and visualizing large amounts of financial data in MATLAB®.
- Machine Learning for Statistical Arbitrage II: Feature Engineering and Model Development
Create a continuous-time Markov model of limit order book (LOB) dynamics, and develop a strategy for algorithmic trading based on patterns observed in the data.
- Machine Learning for Statistical Arbitrage III: Training, Tuning, and Prediction
Use Bayesian optimization to tune hyperparameters in the algorithmic trading model, supervised by the end-of-day return.
- Backtest Deep Learning Model for Algorithmic Trading of Limit Order Book Data
Apply a backtest strategy to measure the performance of a long short-term memory (LSTM) neural network, which is trained and validated on limit order book (LOB) data of a security.