Brain Machine Learning proprietary platform is exploited to generate a daily stock ranking based on the predicted future returns of a universe of 1000 stocks on two time horizons: 5 and 10 days.
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. The stock universe is represented by the 1000 US stocks with the largest market cap and is updated every year. The model is trained and tested with a walking forward approach.
The model uses several types of input data. Some examples are:
- Time varying stock specific features like price and volume related metrics or fundamentals
- Time fixed stock specific features like the sector and other database information
- Market regime features such as volatility and other financial stress indicators
- Calendar features representing possible anomalies, for example the month of the year
- Enhance quantitative models and long short strategies by adding a stock ranking that non-linearly combines stock specific market data (price, volume, fundamentals) with market regimes indicators and calendar anomalies using advanced Machine Learning techniques.
- Rely on a robust Machine Learning approach that incorporates a series of techniques to mitigate the overfitting problem that often plagues financial data with a low signal to noise ratio. The model uses a dynamic universe that is updated each year to avoid survivorship bias.
- Explore the model data with access to approximately 10 years of daily rankings history.
Quality Data You Can Trust
- Data sourced from Brain
- Data is updated at 6AM UTC for the current day. The update refers to the stock ranking based on the prediction of stock future returns for next 5 days and next 10 days
- Daily frequency, history dating back to January 1, 2010
Intrinio makes securing the best financial data easier and more affordable than ever. Take your pick from hundreds of high-quality international and domestic feeds, many of which can be redistributed without penalty or additional fees. Let us clean up the messy parts of data collection and standardization so you can spend more time working on what matters.