Data-driven prediction and classification of multi-component alloys using interpretable machine learning

Abstract The design of advanced metallic alloys is challenged by complex, nonlinear interactions among multiple alloying elements, making conventional trial-and-error approaches costly and time-intensive. This study presents an integrated, interpretable machine learning framework applied to a dataset of 2,672 multi-component alloy systems, using elemental composition as the sole input. A multi-output Random Forest Regressor simultaneously predicts Ultimate Tensile Strength (UTS) and Liquidus Temperature, achieving a test R² of 0.848 and a 5-fold cross-validation R² of 0.849 ± 0.017, outperforming Linear Regression (R² = 0.512) and Gradient Boosting (R² = 0.787) baselines. A Logistic Regression classifier identifies high-performance alloy compositions defined by simultaneous UTS and liquidus temperature thresholds achieving an overall accuracy of 82% and an AUC of 0.871. Threshold sensitivity analysis confirms classification stability across varying performance criteria. Principal Component Analysis (PCA) and K-Means clustering , applied to the full compositional feature space, reveal three distinct alloy families with systematic differences in mechanical and thermal properties. Critically, interpretability is preserved throughout via SHAP analysis and permutation-based feature importance, identifying Vanadium (V), Iron (Fe), Tungsten (W), and Carbon (C) as the dominant compositional drivers a finding that both confirms and extends established metallurgical understanding. The dataset was verified to contain no missing values across all 31 elemental features. Collectively, the proposed framework provides a scalable and interpretable foundation for accelerated alloy screening, property prediction, and data-driven materials discovery.