The stock market prediction process is carried out to forecast the future price movement of a stock. It involves using various analytical techniques and procedures. The process utilized in forecasting the future price movement of stocks involves using various techniques and methods. It is very challenging to predict the stock market's direction due to the multitude of factors that can affect its performance, such as economic indicators, corporate events, and investor sentiments. Data mining techniques have gained popularity in the field of forecasting the stock market, as they can extract valuable information from vast amounts of data. This paper presents an empirical study on the use of these techniques to predict the stock market trends. The study utilizes four popular mining algorithms SVM, Linear Regression, Random Forest (RF) and Naïve Bayes. The objective of the study was to analyze the effects of various factors on stock prices of major technology companies. These included the volume of trading, the priceto earnings ratio, and the news sentiment score. The results of the tests revealed that the RF performed better than the others in terms of accuracy. The former performed well when all of the available factors were utilized, while the latter performed even better when only a single factor was used. Although the Naive Bayes and linear regression algorithms performed well, their accuracy rates were not as high as those of the two others. The findings of the study show that data mining techniques can effectively predict the stock market's direction.

Stock market, Data mining, Machine learning, Prediction