Stock price prediction using machine learning algorithms

Stock prices are difficult to predict as they are affected by many variables. However, it is possible to predict stock prices with today's computers using machine learning algorithms. In our study, the daily value prediction was made by collecting the data of the first 5 stocks with the highest market value traded in the BIST 100 between 2016-2020 for about 5 years. Multiple linear regression, bayesian regression, random forest regression, decision tree regression, support vector regression, artificial neural network algorithms were applied to include maximum 22 features in machine learning and the results were compared. The most successful result was obtained in the artificial neural networks algorithm. Normalization, cross validation, parameter optimization, feature selection have been applied to achieve the highest success.