.png){kind=icon}
返回
Designing a feature selection method based on explainable artificial intelligence
.png){kind=icon}
OA
AI
DOI：10.1007/s12525-022-00608-1.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Nowadays, artificial intelligence (AI) systems make predictions in numerous high stakes domains, including credit-risk assessment and medical diagnostics. Consequently, AI systems increasingly affect humans, yet many state-of-the-art systems lack transparency and thus, deny the individual's right to explanation . As a remedy, researchers and practitioners have developed explainable AI, which provides reasoning on how AI systems infer individual predictions. However, with recent legal initiatives demanding comprehensive explainability throughout the (development of an) AI system, we argue that the pre-processing stage has been unjustifiably neglected and should receive greater attention in current efforts to establish explainability. In this paper, we focus on introducing explainability to an integral part of the pre-processing stage: feature selection. Specifically, we build upon design science research to develop a design framework for explainable feature selection. We instantiate the design framework in a running software artifact and evaluate it in two focus group sessions. Our artifact helps organizations to persuasively justify feature selection to stakeholders and, thus, comply with upcoming AI legislation. We further provide researchers and practitioners with a design framework consisting of meta-requirements and design principles for explainable feature selection.
Keyword:
Explainable artificial intelligence
Machine learning
Feature selection
Design science research
SHAP values
Preprocessing
期刊
IF:
6.8
论文数:
913
被引数:
4.3K
机构
引用论文
Degradation of reactive dyes I. A comparative study of ozonation, enzymatic and photochemical processes活性染料的降解I.臭氧、酶和光化学过程的比较研究.png)
Chemosphere
ChemosphereIF0
PREAI
分享收藏Effect of lasalocid or salinomycin administration on performance and immunity following coccidia vaccination of commercial broilers施用lasalocid或盐霉素对商业肉鸡接种球虫后性能和免疫力的影响
OAAI
OAAI分享收藏PERCEIVED USEFULNESS, PERCEIVED EASE OF USE, AND USER ACCEPTANCE OF INFORMATION TECHNOLOGY感知有用性、感知易用性和用户对信息技术的接受度
PREAI
分享收藏Controlling RDX explosive crystallite morphology and inclusion content via simple ultrasonic agitation and solvent evaporationCrystEngComm
CrystEngCommIF0
PREAI
分享收藏
查看更多内容