{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T07:09:18Z","timestamp":1784704158984,"version":"3.55.0"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T00:00:00Z","timestamp":1784678400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T00:00:00Z","timestamp":1784678400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Data Sci Anal"],"published-print":{"date-parts":[[2026,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Interpreting machine learning models fairly and efficiently remains challenging, particularly when features are correlated. Classical Shapley-based explanations can split attribution among substitutes and are often computationally demanding. This study presents\n                    <jats:italic>iAdditive<\/jats:italic>\n                    , a model-agnostic approach that promotes fairness by grouping highly correlated or redundant features through group-level attribution semantics and improves efficiency via a dynamic coalition heuristic inspired by additive explanation methods. Experiments on simulated datasets with known structure and on NHANES indicate that iAdditive produces faithful global attributions under correlation while achieving substantial runtime reductions compared with KernelSHAP, TreeSHAP, SAGE, and exact Shapley baselines. By balancing fairness, interpretability, and efficiency, iAdditive provides a practical tool for trustworthy decision support in applications such as health care.\n                  <\/jats:p>","DOI":"10.1007\/s41060-026-01221-7","type":"journal-article","created":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T06:54:45Z","timestamp":1784703285000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["iAdditive: fast and fair Shapley-inspired feature attribution for correlated features"],"prefix":"10.1007","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4038-3566","authenticated-orcid":false,"given":"Abirami","family":"Gunasekaran","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6628-1421","authenticated-orcid":false,"given":"Minsi","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0105-7730","authenticated-orcid":false,"given":"Richard","family":"Hill","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keith","family":"McCabe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,22]]},"reference":[{"key":"1221_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103502","volume":"298","author":"KJ Aas","year":"2021","unstructured":"Aas, K.J., Jullum, M., L\u00f8land, A.: Explaining individual predictions when features are dependent: more accurate approximations to Shapley values. Artif. Intell. 298, 103502 (2021)","journal-title":"Artif. Intell."},{"key":"1221_CR2","doi-asserted-by":"publisher","first-page":"43544","DOI":"10.1007\/s11356-021-13255-4","volume":"28","author":"OF AlThuwaynee","year":"2021","unstructured":"AlThuwaynee, O.F., Kim, S.-W., Najemaden, M.A., Aydda, A., Balogun, A.-L., Fayyadh, M.M., Park, H.-J.: Demystifying uncertainty in PM10 susceptibility mapping using variable drop-off in extreme-gradient boosting (XGB) and random forest (RF) algorithms. Environ. Sci. Pollut. Res. 28, 43544\u201343566 (2021)","journal-title":"Environ. Sci. Pollut. Res."},{"key":"1221_CR3","doi-asserted-by":"crossref","unstructured":"Basu, I., Maji, S.: \u201cMulticollinearity correction and combined feature effect in Shapley values\u201d. In: Australasian Joint Conference on Artificial Intelligence. Springer, 79\u201390 (2022)","DOI":"10.1007\/978-3-030-97546-3_7"},{"key":"1221_CR4","doi-asserted-by":"crossref","unstructured":"Biecek, P., Burzykowski, T.: Explanatory Model Analysis. Chapman and Hall\/CRC, New York (2021)","DOI":"10.1201\/9780429027192"},{"issue":"5","key":"1221_CR5","doi-asserted-by":"publisher","first-page":"1726","DOI":"10.1016\/j.cor.2008.04.004","volume":"36","author":"J Castro","year":"2009","unstructured":"Castro, J., G\u00f3mez, D., Tejada, J.: Polynomial calculation of the Shapley value based on sampling. Comput. Operations Res. 36(5), 1726\u20131730 (2009)","journal-title":"Comput. Operations Res."},{"key":"1221_CR6","unstructured":"Catav, A., Fu, B., Zoabi, Y., Meilik, A.L.W., Shomron, N., Ernst, J., Sankararaman, S., Gilad-Bachrach, R.: \u201cMarginal contribution feature importance-an axiomatic approach for explaining data\u201d. In: International conference on machine learning. PMLR, 1324\u20131335 (2021)"},{"issue":"6","key":"1221_CR7","doi-asserted-by":"publisher","first-page":"590","DOI":"10.1038\/s42256-023-00657-x","volume":"5","author":"H Chen","year":"2023","unstructured":"Chen, H., Covert, I.C., Lundberg, S.M., Lee, S.-I.: Algorithms to estimate Shapley value feature attributions. Nature Mach. Intell. 5(6), 590\u2013601 (2023)","journal-title":"Nature Mach. Intell."},{"key":"1221_CR8","unstructured":"Chen, J., Song, L., Wainwright, M.J., Jordan, M.I.: \u201cL-Shapley and C-Shapley: Efficient Model Interpretation for Structured Data\u201d. In: International Conference on Learning Representations (2018)"},{"key":"1221_CR9","unstructured":"Cohen, B.B.: Plan and operation of the NHANES I Epidemiologic Followup Study, 1982-84. 22. US Department of Health and Human Services, Public Health Service, Centers for Disease Control, National Center for Health Statistics, 1992 (1987)"},{"key":"1221_CR10","first-page":"17212","volume":"33","author":"I Covert","year":"2020","unstructured":"Covert, I., Lundberg, S.M., Lee, S.-I.: Understanding global feature contributions with additive importance measures. Adv. Neural. Inf. Process. Syst. 33, 17212\u201317223 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1221_CR11","unstructured":"Cox, C.S.: Plan and operation of the NHANES I Epidemiologic Followup Study, 1987. 27. US Department of Health and Human Services, Public Health Service, Centers for Health Statistics (1992)"},{"key":"1221_CR12","unstructured":"Cox, C.S., Feldman, J.J., Golden, C.D., Lane, M.A., Madans, J.H., Mussolino, M.E., Rothwell, S.T.: \u201cPlan and operation of the NHANES I Epidemiologic Followup Study, 1992\u201d. (1997)"},{"key":"1221_CR13","doi-asserted-by":"crossref","unstructured":"Deng, X., Papadimitriou, C.H.: On the complexity of cooperative solution concepts. Math. Oper. Res. 19(2), 257\u2013266 (1994)","DOI":"10.1287\/moor.19.2.257"},{"key":"1221_CR14","unstructured":"Edden, G.: Naive Shapley method. https:\/\/edden-gerber.github.io\/shapley-part-2\/(2019)"},{"key":"1221_CR15","doi-asserted-by":"crossref","unstructured":"Feltkamp, V.: \u201cAlternative axiomatic characterizations of the Shapley and Banzhaf values\u201d. In: International Journal of Game Theory 24.2, 179\u2013186 (1995)","DOI":"10.1007\/BF01240041"},{"key":"1221_CR16","unstructured":"Fern\u00e1ndez-Delgado, M., Cernadas, E., Barro, S., Amorim, D.: \u201cDo we need hundreds of classifiers to solve real world classification problems?\u201d In: The journal of machine learning research 15.1, 3133\u20133181 (2014)"},{"key":"1221_CR17","unstructured":"Finucane, F.F., Freid, V.M., Madans, J.H., Cox, C.S., Kleinman, J.C., Rothwell, S.T., Barbano, H.E., Feldman, J.J.: \u201cPlan and operation of the NHANES I Epidemiologic Followup Study, 1986.\u201d In: Vital and Health statistics. Ser. 1, Programs and Collection Procedures 25, 1\u2013154 (1990)"},{"key":"1221_CR18","doi-asserted-by":"crossref","unstructured":"Fryer, D., Str\u00fcmke, I., Nguyen, H.: \u201cShapley value confidence intervals for attributing variance explained\u201d. In: Frontiers in Applied Mathematics and Statistics 6, 587199 (2020)","DOI":"10.3389\/fams.2020.587199"},{"key":"1221_CR19","doi-asserted-by":"crossref","unstructured":"Guidotti, R., Monreale, A., Ruggieri, S., Turini, F., Giannotti, F., Pedreschi, D.: \u201cA survey of methods for explaining black box models\u201d. In: ACM computing surveys (CSUR) 51.5, 1\u201342 (2018)","DOI":"10.1145\/3236009"},{"key":"1221_CR20","doi-asserted-by":"crossref","unstructured":"Gunasekaran, A., Chen, M., Hill, R., McCabe, K.: \u201cMethod agnostic model class reliance (mamcr) explanation of multiple machine learning models\u201d. In: International Conference on Soft Computing and its Engineering Applications. Springer, 56\u201371 (2022)","DOI":"10.1007\/978-3-031-27609-5_5"},{"key":"1221_CR21","doi-asserted-by":"crossref","unstructured":"Gunasekaran, A., Mistry, P., Chen, M.: \u201cWhich Explanation Should be Selected: A Method Agnostic Model Class Reliance Explanation for Model and Explanation Multiplicity\u201d. In: SN Computer Science 5.5, 503 (2024)","DOI":"10.1007\/s42979-024-02810-8"},{"key":"1221_CR22","unstructured":"Janzing, D., Minorics, L., Bl\u00f6baum, P.: \u201cFeature relevance quantification in explainable AI: A causal problem\u201d. In: International Conference on artificial intelligence and statistics. PMLR, 2907\u20132916 (2020)"},{"key":"1221_CR23","unstructured":"Lundberg, S.M., Lee, S.-I.: \u201cA unified approach to interpreting model predictions\u201d. In: Advances in neural information processing systems 30 (2017a)"},{"key":"1221_CR24","unstructured":"Lundberg, S.M., Lee, S.-I.: \u201cConsistent feature attribution for tree ensembles\u201d. (2017b) In: arXiv preprint arXiv:1706.06060"},{"key":"1221_CR25","doi-asserted-by":"crossref","unstructured":"Maasland, T., Pereira, J., Bastos, D., de Goffau, M., Nieuwdorp, M., Zwinderman, A.H., Levin, E.: \u201cInterpretable models via pairwise permutations algorithm\u201d. In: Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer, 15\u201325 (2021)","DOI":"10.1007\/978-3-030-93736-2_2"},{"key":"1221_CR26","unstructured":"Merkle, M.: Mortality Prediction and Interpretation. (2021) https:\/\/deepnote.com\/@marius-merkle-b139\/CS-209A-Final-Project-Mortality-Prediction-and-Interpretation-90d233cc-796e-4122-8918-65c857662818"},{"key":"1221_CR27","unstructured":"Molnar, C.: \u201cInterpretable Machine Learning\u201d. In: Christophm. github. io (2020)"},{"key":"1221_CR28","first-page":"307","volume":"2","author":"LS Shapley","year":"1953","unstructured":"Shapley, L.S.: A value for n-person games. Contributions to the Theory of Games 2, 307\u2013317 (1953)","journal-title":"Contributions to the Theory of Games"},{"key":"1221_CR29","doi-asserted-by":"crossref","unstructured":"Staniak, M., Biecek, P.: \u201cExplanations of model predictions with Live and BreakDown packages\u201d. (2018) In: arXiv preprint arXiv:1804.01955","DOI":"10.32614\/RJ-2018-072"},{"key":"1221_CR30","doi-asserted-by":"crossref","unstructured":"\u0160trumbelj, E., Kononenko, I.: \u201cExplaining prediction models and individual predictions with feature contributions\u201d. In: Knowledge and information systems 41.3, 647\u2013665 (2014)","DOI":"10.1007\/s10115-013-0679-x"},{"key":"1221_CR31","doi-asserted-by":"crossref","unstructured":"Webber, W., Moffat, A., Zobel, J.: \u201cA similarity measure for indefinite rankings\u201d. In: ACM Transactions on Information Systems (TOIS) 28.4, 1\u201338 (2010)","DOI":"10.1145\/1852102.1852106"},{"key":"1221_CR32","doi-asserted-by":"crossref","unstructured":"Zhao, C., Liu, J., Parilina, E.: \u201cComplete-to-sparse: A novel graph construction strategy for efficient ShapG\u201d. In: International Conference on Mathematical Optimization Theory and Operations Research. Springer, 180\u2013194 (2025a)","DOI":"10.1007\/978-3-031-97077-1_13"},{"key":"1221_CR33","doi-asserted-by":"publisher","unstructured":"Zhao, C., Liu, J., Parilina, E.: \u201cShapG: New feature importance method based on the Shapley value\u201d. In: Engineering Applications of Artificial Intelligence 148, 110409. ISSN: 0952-1976. (2025b) https:\/\/doi.org\/10.1016\/j.engappai.2025.110409","DOI":"10.1016\/j.engappai.2025.110409"},{"key":"1221_CR34","doi-asserted-by":"crossref","unstructured":"Ziweritin, S., Gunasekaran, A., Iram, S., Chen, M.: \u201cDissecting deep models: removal and zeroing-based explanation (RZE) techniques\u201d. In: Evolving Systems 17.3, 81 (2026)","DOI":"10.1007\/s12530-026-09840-y"}],"container-title":["International Journal of Data Science and Analytics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41060-026-01221-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s41060-026-01221-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41060-026-01221-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T06:55:11Z","timestamp":1784703311000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s41060-026-01221-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,22]]},"references-count":34,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,12]]}},"alternative-id":["1221"],"URL":"https:\/\/doi.org\/10.1007\/s41060-026-01221-7","relation":{},"ISSN":["2364-415X","2364-4168"],"issn-type":[{"value":"2364-415X","type":"print"},{"value":"2364-4168","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,22]]},"assertion":[{"value":"25 February 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 July 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no conflict of interest.","order":1,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable\u2014this study uses publicly available datasets and does not involve human participants or identifiable personal data.","order":2,"name":"Ethics","label":"Ethics Approval and Consent to Participate","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"240"}}