Machine learning has become an increasingly important technique in factor investing and quantitative trading. With open source python libraries and frameworks available, investors can backtest factor models and trading strategies at scale. In this article, we will introduce some of the best open source machine learning tools for factor investing and where to find example code.
Zipline and Quantopian for backtesting systematic trading strategies
Zipline and Quantopian are two of the most popular open source python libraries for backtesting trading strategies and analyzing financial data. They provide vectorized backtesting frameworks to quickly test ideas across thousands of stocks with pandas. Quantopian also hosted a platform to build and execute algorithms. Key features include efficient factor construction, portfolio optimization, risk modeling, interactive charts etc.
Machine learning in jesse crypto trading bot framework optimized for live trading
null
Tensorflow and PyTorch for deep learning based strategies
Some of the most advanced machine learning techniques used in finance involves deep neural networks implemented with frameworks like Tensorflow and PyTorch. Researchers have shown significant alpha can be generated from RNNs and other deep networks when applied to factor investing and systematic trading strategies.
This article covered some best open source tools like Zipline, Pyfolio, Empyrical for backtesting and optimizing machine learning powered factor investing strategies. Quantopian and jesse are great for extending models to live trading. With blogs and example github code repositories available, investors can quickly get started with cutting edge techniques.