A study on the prediction of the direction of the stock market index with artificial intelligence methods: Comparative analysis

In this study, the direction of the Bist100 index will be tried to be estimated by using Regression Analysis and Support vector machines, which are sub-branches of Machine learning, and Technical analysis indicators and the results will be compared. At the end of the study, it will be decided which is the best method and technique for the estimation of the Bist100 index. During the implementation phase, applications will be made and simulated with each of the Logistic Regression, Lasso Regression, Ridge Regression and Support Vector Machine prediction models using the daily and 60-minute time series data sets of the Bist100 index, and the results will be evaluated separately for each model. The model with the best results will be used together with technical analysis indicators to try to obtain the best method for Bist100 index estimation.