Boglehead investing, founded on the principles of John C. Bogle is one of the classic time tested long term, low cost, and passive investment strategy. This paper uses various machine learning methods, and fundamental stock data in order to predict whether or not a stock would incur negative returns next year, and suggests a loss averted bogle-head strategy to invest in all stocks which are expected to not give negative returns over the next year. Results reveal that XGBoost, out of the 44 models trained, has the highest classification metrics for this task. Furthermore, this paper shall use various machine learning methods for exploratory data analysis, and SHAP values reveal that Net Income Margin, ROA, Gross Profit Margin and EBIT are some of the most important factors for this. Also, based on the SHAP values it is interesting to note that the current year has negligible contribution to the final prediction. Investors can use this as a heuristic guide for loss averted long term (1-year) stock portfolios.

Gradient boosting is a widely used machine learning algorithm for tabular regression, classification and ranking. Although, most of the open source implementations of gradient boosting such as XGBoost, LightGBM and others have used decision trees as the sole base estimator for gradient boosting. This paper, for the first time, takes an alternative path of not just relying on a static base estimator (usually decision tree), and rather trains a list of models in parallel on the residual errors of the previous layer and then selects the model with the least validation error as the base estimator for a particular layer. This paper has achieved state-of-the-art results when compared to other gradient boosting implementations on 50+ tabular regression and classification datasets. Furthermore, ablation studies show that MSBoost is particularly effective for small and noisy datasets. Thereby, it has a significant social impact especially in tabular machine learning problems in the domains where it is not feasible to obtain large high quality datasets.