2026-10-12T12:24:24Z https://api.figshare.com/v2/oai

oai:figshare.com:article/34016427 2026-09-28T17:34:15Z category_15 category_21 category_734 category_931 category_106 portal_5 item_type_3 month_year_09_2026

<p>Variable description and encoding.</p> Juntao Chen (6415844) Jinmei Zhan (25132656) Xiaodeng Zhou (20300145) Jiahua Yao (20300148) Su-Kit Tang (20300151) Xia Liu (117318) Neuroscience Biotechnology Biological Sciences not elsewhere classified Information Systems not elsewhere classified Science Policy volunteer service hours tertiary vocational colleges structured parzen estimator proposed model achieves mitigate overfitting risk dataset comprises 2 8 %, 3 8 %, 17 22 informative variables 2016 &# 8211 rf ), k recursive feature elimination xgboost classifier using tpe hyperparameter optimization fine &# 8211 optimized xgboost model optimized xgboost knn ), feature set urgent need three fine test split test set stratified 5 smooth employment overall accuracy nearest neighbor logistic regression including non grained prediction grained classes gaokao scores fold cross extracurricular engagement entrance scores employment destinations class distribution balanced accuracy averaged specificity averaged recall averaged precision averaged f1 academic records 4 %). 270 graduates 2019 cohorts 20 train <div><p>Predicting tertiary vocational college students’ employment destinations has become an urgent need for most tertiary vocational colleges. This study proposes a machine learning framework based on Tree-structured Parzen Estimator (TPE)-Optimized eXtreme gradient boosting (XGBoost) for fine-grained prediction of tertiary vocational college students’ employment destinations. The dataset comprises 2,270 graduates (2016–2019 cohorts) from a single tertiary vocational college in China, characterized by 27 features spanning demographics, entrance scores, academic records, and extracurricular engagement. Employment destinations are categorized into three fine-grained classes: smooth employment, further study, and unemployment (class distribution: 78.8%, 17.8%, 3.4%). Recursive Feature Elimination (RFE) reduced the feature set to 22 informative variables. TPE hyperparameter optimization (100 iterations) was applied to the XGBoost classifier using an 80/20 train-test split, with stratified 5-fold cross-validation to mitigate overfitting risk. The proposed model achieves an overall accuracy of 81.72% and a balanced accuracy of 48.80% on the held-out test set, with macro-averaged precision of 0.6608, macro-averaged recall of 0.4880, macro-averaged specificity of 0.7659, and macro-averaged F1-score of 0.5263, outperforming seven baseline classifiers, including non-optimized XGBoost, logistic regression (LR), decision tree (DT), support vector machine (SVM), random forest (RF), K-nearest neighbor (KNN), and LightGBM. SHAP analysis identifies academic GPA across multiple semesters, Gaokao scores, and volunteer service hours as the most influential predictors.</p></div> 2026-09-28T17:33:58Z Dataset Dataset 10.1371/journal.pone.0359421.t003 https://figshare.com/articles/dataset/_p_Variable_description_and_encoding_p_/34016427 CC BY 4.0