arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2307.09191cs.LG
收藏

用于二分类的分类编码器基准

A benchmark of categorical encoders for binary classification

Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院)

Federico Matteucci, Vadim Arzamasov, Klemens Boehm

AI总结:

本文构建了迄今最全面的二分类分类编码器基准,评估32种编码器配置、36种实验因素组合及50个数据集,揭示了数据集选择、实验因素与聚合策略对基准结论的深远影响。

摘要:

分类编码器将分类特征转换为数值表示,这对于广泛的机器学习模型是不可或缺的。现有编码器基准研究由于在(1)编码器、(2)实验因素和(3)数据集的选择上受限而缺乏泛化能力。此外,采用不同的聚合策略也会导致不一致性。本文是迄今为止最全面的分类编码器基准,对来自不同类别的32种编码器配置、36种实验因素组合以及50个数据集进行了广泛评估。研究表明,数据集选择、实验因素和聚合策略对基准结论有深远影响——这些方面在先前的编码器基准中被忽视了。

英文摘要:

Categorical encoders transform categorical features into numerical representations that are indispensable for a wide range of machine learning models. Existing encoder benchmark studies lack generalizability because of their limited choice of (1) encoders, (2) experimental factors, and (3) datasets. Additionally, inconsistencies arise from the adoption of varying aggregation strategies. This paper is the most comprehensive benchmark of categorical encoders to date, including an extensive evaluation of 32 configurations of encoders from diverse families, with 36 combinations of experimental factors, and on 50 datasets. The study shows the profound influence of dataset selection, experimental factors, and aggregation strategies on the benchmark's conclusions -- aspects disregarded in previous encoder benchmarks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑