December 2021 | Choosing Outperforming Stocks with Machine Learning
This study examines the trailing twelve-month returns (TTM) of the stocks in the S&P 500 to see if financial ratios can be leveraged to predict stocks that outperform the market using machine learning. Over the past 12 months, the S&P 500 has returned roughly 26% to investors, so that would be the return realized if passively invested in the index. However, as we know, many investors would much rather prefer excess returns by making savvy stock picks. In the past, these stock picks were made based on fundamental research to determine intrinsic value. Machine learning has brought about a new wave of investing where stock picks may be automated in order to outperform the market. In this study, I see if several machine learning algorithms such as Random Forest, Gaussian Naive Bayes, and SVCs can predict stocks that outperform the market. The models will be fed several financial metrics in an attempt to predict outperforming stocks.
View my Deepnote script HERE