Nonparametric Feature Impact and Importance

作者
Terence Parr,James David Wilson,Jeff Hamrick
出处
期刊:Cornell University - arXiv [Cornell University]
被引量:7
标识
DOI:10.48550/arxiv.2006.04750
摘要

Practitioners use feature importance to rank and eliminate weak predictors during model development in an effort to simplify models and improve generality. Unfortunately, they also routinely conflate such feature importance measures with feature impact, the isolated effect of an explanatory variable on the response variable. This can lead to real-world consequences when importance is inappropriately interpreted as impact for business or medical insight purposes. The dominant approach for computing importances is through interrogation of a fitted model, which works well for feature selection, but gives distorted measures of feature impact. The same method applied to the same data set can yield different feature importances, depending on the model, leading us to conclude that impact should be computed directly from the data. While there are nonparametric feature selection algorithms, they typically provide feature rankings, rather than measures of impact or importance. They also typically focus on single-variable associations with the response. In this paper, we give mathematical definitions of feature impact and importance, derived from partial dependence curves, that operate directly on the data. To assess quality, we show that features ranked by these definitions are competitive with existing feature selection techniques using three real data sets for predictive tasks.

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
刚刚
大个的应助被阿斯蒂芬采纳,获得10
刚刚
甜菜完成签到 ,获得积分10
1秒前
1秒前
顺心的飞柏完成签到 ,获得积分10
1秒前
2秒前
英姑的应助被科研通管家采纳,获得10
2秒前
2秒前
深情安青的应助被科研通管家采纳,获得10
2秒前
绿叶发布了新的文献求助10
2秒前
2秒前
2秒前
健忘不言完成签到,获得积分10
2秒前
顾矜的应助被科研通管家采纳,获得20
2秒前
斯文败类的应助被刻苦夜雪采纳,获得10
2秒前
Liu_letters的应助被科研通管家采纳,获得10
2秒前
xfy的应助被科研通管家采纳,获得10
3秒前
情怀的应助被科研通管家采纳,获得10
3秒前
supshuo的应助被科研通管家采纳,获得20
3秒前
3秒前
我是老大的应助被科研通管家采纳,获得10
3秒前
CodeCraft的应助被科研通管家采纳,获得10
3秒前
3秒前
4秒前
4秒前
4秒前
4秒前
传奇3的应助被zhangkai6633采纳,获得10
4秒前
4秒前
称心的绿竹完成签到,获得积分10
4秒前
朴实归尘发布了新的文献求助10
5秒前
努力地小夏完成签到,获得积分10
5秒前
hhhhh的应助被将匀升采纳,获得10
5秒前
伯赏夜南发布了新的文献求助10
5秒前
小马甲的应助被小赵采纳,获得10
5秒前
5秒前
11155发布了新的文献求助10
6秒前
隐形曼青的应助被zys采纳,获得10
6秒前
赘婿的应助被YK采纳,获得10
7秒前
1096发布了新的文献求助10
7秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
What Else Can I Tell You?: A Pragmatic Study of English Rhetorical Questions as Discursive and Argumentative Acts 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8163835
求助须知:如何正确求助?哪些是违规求助? 9557925
关于积分的说明 21742693
捐赠科研通 7754454
什么是DOI,文献DOI怎么找? 3428350
关于科研通互助平台的介绍 2553034
邀请新用户注册赠送积分活动 2472982