Forecasting BIST100 Index with Macroeconomic Indicators: A Comparative Analysis with Machine Learning Models

In this study, four different Machine Learning (ML) algorithms were used to predict the BIST100 index based on various economic and financial indicators. The predictions were generated using Python for the Random Forest (RF), Categorical Boosting (CatBoost), Gradient Boosting (GB), and Ridge Regression (RR) algorithms. Performance metrics such as Mean Absolute Percentage Error (MAPE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and the Coefficient of Determination (R2) were used to evaluate and compare the models. In conclusion, the best-performing algorithm based on the MAPE metric was found to be RF, with a value of 3.49%. Additionally, feature importance analyses were conducted for each algorithm, and the variables were ranked from the most to the least influential.