The DOI matches its Crossref record; 93 of the 93 references it cites were found in a registry or an index.
Designing a feature selection method based on explainable artificial intelligence
Open accessAbstract
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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Zacharias et al. [169] explained that the feature importance technique seeks to improve explanatory depth by pinpointing the most significant features influencing an AI model's decisions.”
From Recent Emerging Techniques in Explainable Artificial Intelligence to Enhance the Interpretable and Understanding of AI Models for Human (2025) · cites this paper as [169]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Perceived usefulness, perceived ease of use, and user acceptance of information technology
Davis, F. D. (1989) · MIS Quarterly · doi:10.2307/249008 · Cited by 68,483
Three Approaches to Qualitative Content Analysis
Hsieh, H.-F., & Shannon, S. E. (2005) · Qualitative Health Research · doi:10.1177/1049732305276687 · Cited by 44,601
A Unified Approach to Interpreting Model Predictions
Lundberg, S., & Lee, S.-I. (2017) · arXiv · doi:10.48550/arxiv.1705.07874 · Cited by 23,707
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939778 · Cited by 17,555
Seeking Qualitative Rigor in Inductive Research: Notes on the Gioia Methodology
Gioia, D. A., Corley, K. G., & Hamilton, A. L. (2013) · Organizational Research Methods · doi:10.1177/1094428112452151 · Cited by 13,227
Gauriat, C.-M., Pencolé, Y., Ribot, P., et al. (2024) · HAL · doi:10.4230/oasics.dx.2024.27 · Cited by 12,623
Design Science in Information Systems Research1
Hevner, A. R., March, S. T., Park, J., & Ram, S. (2004) · MIS Quarterly · doi:10.2307/25148625 · Cited by 10,707 · cited 3×
“According to Hevner et al. (2004), design science “creates and evaluates [information systems (IS)] artifacts intended to solve identified organizational problems”.”
BackgroundInfluentialFrom local explanations to global understanding with explainable AI for trees
Lundberg, S. M., Erion, G., Chen, H., DeGrave, A., Prutkin, J. M., Nair, B., Katz, R., Himmelfarb, J., Bansal, N., & Lee, S.-I. (2020) · Nature Machine Intelligence · doi:10.1038/s42256-019-0138-9 · Cited by 10,551
Barredo Arrieta, A., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., Garcia, S., Gil-Lopez, S., Molina, D., Benjamins, R., et al. (2020) · Information Fusion · doi:10.1016/j.inffus.2019.12.012 · Cited by 10,423
Wrappers for feature subset selection
Kohavi, R., & John, G. H. (1997) · Artificial Intelligence · doi:10.1016/s0004-3702(97)00043-x · Cited by 9,096
Research works printed but not linked: 3
- Benavoli, A., Corani, G., Mangili, F., Zaffalon, M., & Ruggeri, F. (2014). A Bayesian Wilcoxon signed-rank test based on the Dirichlet process. International conference on machine learning (pp. 1026–1034). PMLR.
- Mlambo, N., Cheruiyot, W. K., & Kimwele, M. W. (2016). A survey and comparative study of filter and wrapper feature selection techniques. International Journal of Engineering and Science (IJES), 5(8), 57–67.
- Prat, N., Comyn-Wattiau, I., & Akoka, J. (2014). Artifact evaluation in information systems design-science research- A holistic view. Pacific Asia Conference on Information Systems (PACIS), 23, 1–16.
Cited by
Sorted by citations
Mathew, D. E., Ebem, D. U., Ikegwu, A. C., Ukeoma, P. E., & Dibiaezue, N. F. (2025) · Neural Processing Letters · doi:10.1007/s11063-025-11732-2 · Cited by 168
Brusa, E. G. M., Cibrario, L., Delprete, C., & Maggio, L. G. D. (2023) · Applied Sciences · doi:10.3390/app13042038 · Cited by 161
Choudhary, R., Kumar, A., Priyadharsini, C., Naik, M. M., Choudhury, M., & Khan, N. A. (2025) · Scientific Reports · doi:10.1038/s41598-025-09463-4 · Cited by 101
Kruschel, S., Hambauer, N., Weinzierl, S., Zilker, S., Kraus, M., & Zschech, P. (2026) · Business & Information Systems Engineering · doi:10.1007/s12599-024-00922-2 · Cited by 50
Yaprakdal, F., & Arısoy, M. V. (2023) · Applied Sciences · doi:10.3390/app132312946 · Cited by 49
Metadata
- Authors
- Zacharias, J., von Zahn, M., Chen, J., & Hinz, O.
- Affiliations
- Goethe University Frankfurt (DE)
- Corresponding author
- Zacharias, Jan
- Venue
- Electronic Markets
- Published
- 2022-12
- Volume
- 32
- Issue
- 4
- Pages
- 2159-2184
- ISSN
- 1019-6781 (ISSN-L)
- 1422-8890
- OpenAlex
- W4312132544
- Cited by
- 109
- References
- 91
- Citations by year
- 2026: 28 · 2025: 31 · 2024: 31 · 2023: 18 · 2022: 1
- FWCI
- 6.66
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Electronic Markets (publishedVersion, cc-by)
- RePEc: Research Papers in Economics (submittedVersion)
- Econstor (Econstor) (submittedVersion, cc-by)
- Publication Server of Goethe University Frankfurt am Main (Goethe University Frankfurt) (submittedVersion, cc-by)
- Funders
- Johann Wolfgang Goethe-Universität, Frankfurt am Main
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- Physical Sciences › Engineering › Safety, Risk, Reliability and Quality › Safety Systems Engineering in Autonomy
- Keywords
- explainable AI, feature selection, right to explanation, AI transparency, design framework, meta-requirements, design principles, credit risk assessment, medical diagnostics
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
