EXPLORING THE INTERPRETABILITY AND PREDICTIVE POWER OF MACHINE LEARNING MODELS IN TECHNOLOGY INDICES: A CASE STUDY

The paper is a comprehensive study of the performance evaluation of Aselsan in the Borsa Istanbul Technology Index, explaining the interpretability and predictability power of the machine learning models. The study encapsulates the technical indicators and the index data as variables and is conducted in a dataset of 600 days between November 20, 2020, and April 10, 2023. The data was split into two subsets, with 85% allocated to the training subset and 15% to the validation subset. Model training is conducted using the Orthogonal Matching Pursuit (OMP) algorithm. After the training, the model validates its prediction using previously unseen data. The results of the model's findings at this stage indicate the model's strong capacity to predict and robustly predict movements in Aselsan stock prices. Additionally, the model has an interpretability capacity that helps the user understand the decision process and the reasons behind the predictions.