catboost

该论文提出一个临床可解释的机器学习框架，使用CatBoost和自动化的SHAP依赖图定量分析，从NHANES的44个异构临床特征中估计生物年龄。研究发现模型估计的生物年龄与实际年龄高度相关，并识别出血尿素氮、血糖和剧烈运动等关键预测因子。

This paper presents a leakage-safe and scheduler-aware machine learning framework for predicting grid job runtime, using CatBoost with temporal validation to enhance scheduling efficiency in distributed computing environments.

This paper proposes a methodology for predicting B2B customer conversion using document representation, graph theory, and CatBoost, achieving 91% accuracy in sales funnel prediction.

Presents Sim2Win, a team-agnostic event-based system for pre-match outcome prediction and tactical profiling in football, achieving 55.4% accuracy on unseen teams.

This paper presents a controlled comparison of seven categorical encoding methods on the IEEE-CIS fraud dataset, evaluating accuracy, interpretability, and computational trade-offs with a fixed LightGBM learner, finding that entity embeddings achieve the highest AUC-ROC but no encoder dominates both metrics.

This paper presents a machine learning framework using CatBoost and SHAP to predict obstructive coronary artery disease from CT calcium scoring scans, achieving high accuracy by combining calcium-omics and epicardial fat features.

This study presents a hybrid predictive framework using CatBoost and SHAP to identify risk factors in tree-involved traffic crashes, highlighting restraint non-use as the most critical predictor of severe injury.