Analysis of machine learning’s performance in stock market prediction, compared to traditional technical analysis indicators

Abstract

This study compares the performance of machine learning (ML) algorithms with traditional technical indicators in real estate, technology, and healthcare sectors. Unveiling the limitations of classical indicators, particularly their struggle to surpass the 50% threshold, the research explores the predictive capabilities of ML algorithms, focusing on AdaBoost and support vector machine (SVM). The relative strength index (RSI) emerges as a reliable performer for buy decisions but with potential oversight. Results affirm the superiority of ML algorithms in precision, recall, and F1 score, transcending traditional indicators. Sector-specific variations showcase exceptional ML efficacy, particularly in healthcare. Algorithmic evaluation spotlights AdaBoost and SVM, underscoring the importance of strategic selection. The study advocates for a nuanced approach, blending RSI with ML for refined strategies. In conclusion, this research contributes significantly to financial decision-making, exposing limitations and positioning ML algorithms as powerful tools for improved investment strategies.