Optimization of a Genetic Algorithm-Based Machine Learning Model for Predicting the Magnetocaloric Effect of Bulk Metallic Glasses

This study used an XGB model to predict the magnetocaloric effect values of bulk metallic glass materials. A total of 174 composition-based features were obtained using the Python modules 'Pymatgen' and 'Matminer', and a feature selection method was applied to reduce overfitting. First, by examining the Pearson correlation coefficient, we reduced the number of features with high correlations, resulting in 104 features. Second, using the feature importance method provided by the XGB model, 40 key features were identified based on the regression performance results. Finally, through a two-stage genetic algorithm, 12 optimized features were selected, which helped prevent overfitting and improve the prediction performance of the magnetocaloric effect.