What does this research mean for the field?

An XGBoost-SHAP machine learning framework significantly improves the accuracy, reliability, and interpretability of college student entrepreneurship risk assessment by effectively handling complex nonlinear feature interactions. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

Develop an interpretable XGBoost-SHAP predictive model to assess college student entrepreneurship risk by capturing complex nonlinear feature interactions.

August 16, 2026Advanced ElectromagneticsOpen Access

College Student Entrepreneurship Risk Assessment Model Based on XGBoost

View Full Paper

Ask AI

Bookmark

Authors

MGM. GuoElectric Power Research Institute

Discussion

Member takes

Implication

Predictive modeling evaluation shows high accuracy in student entrepreneurship risk assessment, indicating that explainable machine learning improves risk forecasting.

Key Points

Develop an interpretable XGBoost-SHAP predictive model to assess college student entrepreneurship risk by capturing complex nonlinear feature interactions.
Applied data cleaning, encoding, missing-value imputation, and recursive feature elimination combined with XGBoost feature importance to select optimal predictive features.
Optimized model hyperparameters through grid search and cross-validation, applying the SHAP framework to generate global and local feature attribution graphs.
Achieved an average classification accuracy exceeding 0.85, a misclassification rate below 0.15, and an F1-score exceeding 0.87 in multi-scenario evaluation.
Demonstrated cross-disciplinary generalization capability with Cohen's Kappa exceeding 0.71 and area under the receiver operating characteristic curve (AUC) exceeding 0.91.

Cite This Study

M. Guo (2026) studied this question.

synapsesocial.com/papers/6a8179abf2fb91fc834acf13 https://doi.org/10.7716/aem.v15i3.3564

View Full Paper

Ask AI

Bookmark

Implication

Predictive modeling evaluation shows high accuracy in student entrepreneurship risk assessment, indicating that explainable machine learning improves risk forecasting.

College Student Entrepreneurship Risk Assessment Model Based on XGBoost

Discussion

Member takes

Implication

Key Points

Cite This Study

College Student Entrepreneurship Risk Assessment Model Based on XGBoost

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider