Stock Portfolio Optimization with Competitive Advantages (MOAT): A Machine Learning Approach

This paper aimed to develop a useful Machine Learning (ML) model for detecting companies with lasting competitive advantages (companies’ moats) according their financial ratios in order improve the performance of investment portfolios. First, we computed belonging S&P 500. Subsequently, assessed stocks’ moats an evaluation defined between 0 and 5 each ratio. The sum all provided score 100 classify as wide, narrow or null moats. Finally, several ML models were applied classification obtain efficient, faster less expensive method select advantages. main findings are: (1) highest precision is Random Forest; (2) most important are long-term debt-to-net income, Depreciation Amortization (D&A)-to-gross profit, interest expense-to-Earnings Before Interest Taxes (EBIT), Earnings Per Share (EPS) trend. research provides new combination tools information that can portfolios; authors’ knowledge, this has not been done before. algorithm developed limitation calculation since it does consider its cost, price-to-earnings ratio (PE), valuation. Due limitation, represent strategy short-term intraday trading.