首次统一评估五种集成树模型，为葡萄酒质量预测提供可复现的基准。
Wine Quality Prediction with Ensemble Trees: A Unified, Leak-Free Comparative Study
- 构建无数据泄露流程，结合多重优化策略提升模型可靠性。
- 梯度提升表现最优，随机森林在效率上最具性价比。
- 仅用5个关键变量即可保留97%以上预测能力，适合实际部署。
准确且可复现的葡萄酒质量评估对生产控制至关重要，但目前仍依赖主观、耗时的品评小组。本文首次在经典的Vinho Verde红白葡萄酒数据集（分别含1,599和4,898个样本，11个理化属性）上对五种集成学习器（随机森林、梯度提升、XGBoost、LightGBM、CatBoost）进行统一基准测试。采用80:20分层训练测试划分，训练集内使用五折分层组交叉验证，每折进行标准化、SMOTE-Tomek重采样、逆频率成本加权及Optuna超参数搜索（每模型120-200次试验），并执行两阶段特征选择再训练。最终在未触碰测试集上报告加权F1得分。梯度提升在红/白葡萄酒上分别达到0.693±0.028和0.664±0.016的最高精度，随机森林与XGBoost紧随其后，差距在3个百分点内。限制模型仅使用前五个重要变量，维度降低55%，加权F1仅下降2.6（红）和3.0（白）个百分点，表明酒精、挥发性酸度、硫酸盐、游离SO2和氯化物已捕获主要预测信号。在EPYC 9K84/H20节点上的运行时间显示效率差异显著：梯度提升平均需12小时，XGBoost与LightGBM约2-3小时，CatBoost约1小时，随机森林低于50分钟。因此推荐随机森林作为最经济的生产模型，XGBoost与LightGBM适配GPU场景，梯度提升则为离线基准的性能上限。完整流程文档与指标体系为不平衡多分类葡萄酒质量预测提供了可复现基线。
原文摘要 · Abstract (English)
Accurate and reproducible wine-quality assessment is critical for production control yet remains dominated by subjective, labour-intensive tasting panels. We present the first unified benchmark of five ensemble learners (Random Forest, Gradient Boosting, XGBoost, LightGBM, CatBoost) on the canonical Vinho Verde red- and white-wine datasets (1,599 and 4,898 instances, 11 physicochemical attributes). Our leakage-free workflow employs an 80:20 stratified train-test split, five-fold StratifiedGroupKFold within the training set, per-fold standardisation, SMOTE-Tomek resampling, inverse-frequency cost weighting, Optuna hyper-parameter search (120-200 trials per model) and a two-stage feature-selection refit. Final scores on untouched test sets are reported with weighted F1 as the headline metric. Gradient Boosting achieves the highest accuracy (weighted F1 0.693 +/- 0.028 for red and 0.664 +/- 0.016 for white), followed within three percentage points by Random Forest and XGBoost. Limiting each model to its five top-ranked variables lowers dimensionality by 55 percent while reducing weighted F1 by only 2.6 percentage points for red and 3.0 percentage points for white, indicating that alcohol, volatile acidity, sulphates, free SO2 and chlorides capture most predictive signal. Runtime profiling on an EPYC 9K84/H20 node reveals a steep efficiency gradient: Gradient Boosting averages 12 h per five-fold study, XGBoost and LightGBM require 2-3 h, CatBoost 1 h, and Random Forest under 50 min. We therefore recommend Random Forest as the most cost-effective production model, XGBoost and LightGBM as GPU-efficient alternatives, and Gradient Boosting as the accuracy ceiling for offline benchmarking. The fully documented pipeline and metric set provide a reproducible baseline for future work on imbalanced multi-class wine-quality prediction.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。