COMPARATIVE ANALYSIS OF STOCK MARKET PRICE BEHAVIOR THROUGH MACHINE LEARNING APPROACHES

Stock prices reflect the inherent fluctuations of the stock market, making stock trading a challenging endeavor that often results in monetary loss. This research examines the ability of machine learning algorithms to predict stock prices, focusing specifically on K-Nearest Neighbors (KNN), Support Vector Machine (SVM), and Naive Bayes (NB). The study aims to predict stock prices and compare the outcomes of these algorithms based on their accuracy levels to determine the best-performing algorithm for future use. It addresses common limitations in similar studies, such as small sample sizes, limited time frames, and the neglect of external factors that can influence stock prices. By acknowledging these limitations, the study provides a more comprehensive and reliable analysis, highlighting the potential of machine learning algorithms for predicting stock market prices. However, it underscores the importance of considering economic indicators, market sentiment, and geopolitical events when applying machine learning to stock price prediction. This research demonstrates that while these algorithms have significant potential, their application must be guided by a careful evaluation of limitations and external influences to effectively reduce trading risks and enhance investment strategies.