A supervised machine learning in financial forecasting : identifying effective models for the BIST100 index

The purpose of this study is to identify the most effective supervised machine learning models for predicting the financial performance of companies listed on the BIST100 index. In the rapidly evolving field of financial forecasting, machine learning techniques offer robust predictive capabilities. This research evaluates a range of supervised models, including Tree-Based Models (Decision Trees, Bagging, Random Forests, Adaboost, Gradient Boosting Machine (GBM), Light-GBM, XGBoost, CatBoost), Neural Network-based Models (Artificial Neural Networks (ANN), Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Long Short-Term Memory networks (LSTM)), and Instance-based Learning Models (K-Nearest Neighbors (KNN) and Support Vector Machines (SVM)). The models' performance is assessed using comprehensive error metrics such as Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and relative Root Mean Squared Error (rRMSE). The findings reveal that no single machine learning model consistently outperforms others across all companies in the BIST100 index. However, models like XGBoost and Random Forests demonstrate strong and consistent performance, making them particularly effective for financial performance forecasting. Furthermore, deep learning models such as CNNs, RNNs, and LSTMs show promising results, especially for certain firms. The research highlights key insights for investors and financial analysts seeking to leverage machine learning for data-driven decision-making in the Turkish stock market. This study offers a unique contribution to the field by applying and comparing advanced machine learning techniques in the context of the BIST100 index. It provides actionable insights for improving financial prediction accuracy and offers a foundation for further research in other stock market contexts.