Indian Equity Mutual Fund Performance Evaluation and Ranking Using Genetic Algorithm - Optimized Multi-Factor Scoring System

Le résumé fourni par la source

This study proposes a method for analyzing and ranking the best-performing mutual funds in India based on some categorical criteria, focusing specifically on equity funds that have a history of at least three years. The technique employed is using Genetic Algorithm with a multi-factor scoring system that would return a balanced risk-adjusted, high performing fund. Our approach is contrasted with previous research that also utilized Genetic Algorithm, with our unique aspect being the incorporation of 26 fundamental statistical indicators. These fundamentals are analyzed by our custom algorithm, diverging from traditional time series analysis to utilizing statistical data methods like rolling day averages, among others. Prior research related to Indian equity mutual funds mostly centered around performance evaluation through risk-return metrics such as the Sharpe ratio and Jensen's alpha. Non-Conventional methods such as AI-based forecasting, such as neural networks and reinforcement learning, have shown superior results compared to conventional methods in estimating risk-return metrics. Hybrid ensemble learning techniques, like stacking regressors, enhance predictions of fund prices. Genetic Algorithm is used to optimize the selection of mutual fund portfolios. This research builds on existing studies by using a more extensive dataset comprising 26 statistical indicators, enforcing a minimum three years fund lifespan, and implementing an optimal combination of the aforementioned techniques.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.