Brain Machine Learning Stock Ranking
Overview
Brain Machine Learning proprietary platform is exploited to generate a daily stock ranking based on the predicted returns of a universe of the largest US and European stocks on four time horizons: 2,3, 5, 10 and 21 days (other time horizons could be developed and tested upon request).The model implements a voting scheme of machine learning classifiers that non linearly combine a variety of features with a series of techniques aimed at mitigating the well-known overfitting problem for financial data with a low signal to noise ratio.
Input FeaturesThe inputs to the model are represented by stock-specific features like price and volume related metrics (e.g. momentum or mean reversion on various time scales), fundamentals and also market regimes and calendar features.
Stock UniverseThe stock universe is represented by the lagest US and European stocks and it is updated every year.
Free TrialMore than 10 years of history are available as Trial for testing.
Input Features
The inputs to the model are represented by stock-specific features like price and volume related metrics (e.g. momentum or mean reversion on various time scales), fundamentals and also market regimes and calendar features.
Stock Universe
The stock universe is represented by the lagest US and European stocks and it is updated every year.
Free Trial
More than 10 years of history are available as Trial for testing.
Brain Machine Learning proprietary platform is exploited to generate a daily stock ranking based on the predicted returns of a universe of the largest US and European stocks on four time horizons: 2,3, 5, 10 and 21 days. The data are available with daily frequency on a dedicated S3 bucket and more than 10 years of history are available for testing.