Predicting Academic Award Recognition Across Disciplines Using Publication-Based Bibliometric Indices and SHAP-Driven Explainability

Researcher evaluation underpins critical academic decisions, yet traditional bibliometric indicators lack predictive capability and cross-domain generalizability, while most predictive approaches offer limited interpretability and narrow domain validation. This study proposes a SHAP interpretable, multi-domain supervised learning framework for predicting academic award recognition using thirty two publication count-based bibliometric indices. A balanced dataset was constructed across four disciplines, namely Computer Science, Neuroscience, Mathematics, and Civil Engineering, comprising verified awardees from recognized professional societies and matched non-awardee researchers. Eight classifiers were evaluated under stratified five fold cross validation, assessed via accuracy, precision, recall, F1-score, and ROC AUC. The framework achieved domain-specific F1-scores of 0.70 in Computer Science, 0.73 in Neuroscience, 0.72 in Civil Engineering, and 0.78 in Mathematics, with SVM and XGBoost demonstrating the strongest cross-domain robustness across disciplines. SHAP analysis consistently identified normalized h index, h2 family, q2 index, and g index as dominant cross-domain predictors, while domain-specific indicators, including Rm and w indices in Neuroscience and P index in Civil Engineering, reflected disciplinary recognition patterns. By unifying publication-based feature engineering, multi-domain classification, and SHAP explainability within a single reproducible pipeline, this framework offers a scalable, transparent, and evidence-based tool for institutional researcher evaluation.