The stock market is one of the pillars of the international financial system, which has a significant impact on the stability of the economy as a whole and on the performance of individual investors. However, stock price forecasting is notoriously hard, hidden by volatility and noisy data, which prevents model accuracy. To overcome these challenges, we propose, in this research, to use a new hybrid model: PCA-SVR-PSO. Initially the data is preprocessed by the use of Principal Component Analysis (PCA): redundant variables are eliminated and computation is made more straightforward. At the core of it all, Support Vector Regression or SVR solves the problem of nonlinear relation and delivers a high level of forecast accuracy. Finally, PSO is used for optimization of hyper parameters to extract the maximum possible performance. The proposed model is applied for predicting the stock prices with the help of a comprehensive data set of 3543 records, obtained from Bombay Stock Exchange (BSE) over a time span of two decades (2003 to 2023). The experimental results show that there is a significant improvement in the forecast accuracy compared to the current models, proving the effectiveness of the proposed framework. This approach allows individual investors to make informed decisions and contributes to the advancement of theoretical knowledge about stock market behavior, which results in powerful financial analytics.