The stock market demands a precise balance between profitability and risk management, as most investors are risk-averse. Many investors apply multiple techniques to predict stock prices, such as fundamental analysis and technical analysis, as well as talks given by various stock market analysts. ARIMA is a type of time-series analysis used in prediction algorithms, and this study aims to forecast the price of the BSE Stock Exchange (SENSEX) using the ARIMA model with the help of the Econometrics Student Version. The ARIMA model was built using 384 time-series observations collected from January 3, 2023 to July 23, 2024 from the official website of the Bombay Stock Exchange. Augmented Dickey Fuller test was applied to verify whether the selected data set has a unit root or not. The data set is stationary with the first difference d(1). For ARIMA model estimation, significant spikes in the correlogram of the Autocorrelation function and Partial autocorrelation function at lag (1,1,1) (27,1,27) (30,1,30) have been observed and developed ARIMA (Tentative) models at ARIMA(1,1,1), (1,1,27) & (27,1,1), (27,1,27), (1,1,30) (30,1,30) (27,1,30) and executed. The best ARIMA model (27,1,1) was selected based on Sign, Sigmasq, Adj R2, and Akaike Information Criterion (AIC) & Schwarz Criterion(SC). By applying the Correlogram Q statistic of Residual diagnostic check, authors identified a significant spike in the Correlogram at the 30th lag of ACF and PACF. By considering significant spikes, adjusted tentative models developed such as AR(27) AR(30) MA(1) and AR(27) MA(1) MA(30). ARIMA model of AR(27) MA(1) MA(30) was selected based on Sign, Sigmasq, Adj R2, and AIC& SIC to predict the future prices of the BSE Stock Exchange(SENSEX). The findings demonstrated the ARIMA model's strong short-term prediction potential and its ability to compete with other stock price prediction techniques.