Brain

BRAIN is a Research Company that develops proprietary signals based on alternative data and algorithms for investment strategies on financial markets. BRAIN developed proprietary datasets based on standard statistical approaches as well as on Machine Learning and Natural Language Processing techniques. Our main alternative datasets are: A) SENTIMENT ON STOCKS FROM FINANCIAL NEWS Brain Sentiment Indicator on stocks: sentiment at ticker level from financial news using news categorization and a bag of words scheme customized for Finance. One important innovation compared to other vendors is that we also cluster news in topics to renormalize news repetition. B) STOCK RANKING BASED ON MACHINE LEARNING 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 four time horizons: 2,3, 5 and 10 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. C) BRAIN DYNAMIC ALLOCATION A risk on / risk off signal on equity markets based on volatility indicators and other financial stress varibles in order to avoid major financial stress periods. A portfolio of ETFs for main asset classes is optimized according to such signal with the objective of minimum volatility. *Currently we are only providing data to institutional investors and not to retail investors.