A STUDY ON MACHINE LEARNING APPLICATIONS IN STOCK MARKET PRICE PREDICTION USING SECONDARY MARKET DATA

Stock markets are inherently volatile and influenced by a complex interaction of economic indicators, market information, and investor behaviour, making accurate stock price prediction a persistent challenge for investors and financial analysts. Traditional forecasting approaches largely rely on statistical techniques that assume linear relationships among financial variables, which often fail to capture the nonlinear and dynamic patterns present in modern financial markets. With the rapid advancement of computational technology, machine learning techniques have emerged as powerful tools capable of processing large financial datasets and identifying hidden patterns that influence market movements.

The present study investigates the application of machine learning approaches in stock market price prediction using secondary market data obtained from recognized financial databases and stock exchange records. The study adopts a quantitative analytical research design, utilizing key market indicators such as opening price, highest price, lowest price, trading volume, and previous closing price to examine their relationship with stock price movements. Data analysis using correlation and regression techniques reveals a strong positive relationship between historical price indicators and stock closing prices, indicating the relevance of these variables in predictive modeling. The results demonstrate that the analytical model explains a substantial proportion of variation in stock prices, highlighting the capability of machine learning–based approaches to enhance forecasting performance.

The study concludes that data-driven machine learning techniques significantly improve stock market prediction accuracy, thereby providing valuable insights for investors, financial analysts, and policymakers in developing more effective investment and risk management strategies.