{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,21]],"date-time":"2026-06-21T14:48:25Z","timestamp":1782053305047,"version":"3.54.5"},"reference-count":17,"publisher":"European Open Science Publishing","issue":"1","license":[{"start":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T00:00:00Z","timestamp":1769385600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-sa\/4.0"}],"content-domain":{"domain":["eu-opensci.org"],"crossmark-restriction":false},"short-container-title":["EJAI"],"abstract":"<jats:p>Capitalizing latent unobserved structures to improve the accuracy of predictive models has become an active avenue for deep learning research. Most approaches cluster original features to infer latent structures. However, the information gained during the process can often be implicitly derived using sufficiently complex models. Thus, these approaches often provide minimal benefits. We propose a Shapley Additive exPlanations based supervised deep learning framework called FORCE (Feature Oriented Representation with Clustering and Explanation), which relies on a two-stage usage of SHAP values in the neural network architecture, (i) a latent embedding to guide model training based on clustering absolute SHAP values, and (ii) initiating an attention mechanism within the architecture using latent information. This approach gives a neural network an indication of the effect of unobserved values that modify the importance of a feature for an observation. The proposed framework was evaluated using three real-life datasets. Our results demonstrate that FORCE led to dramatic improvements in overall performance as compared to networks that did not incorporate the latent feature and attention framework (for example, F1 score for the presence of Polycystic Ovarian Syndrome 0.99 vs 0.80). Using cluster assignments and attention based on SHAP values guides deep learning, enhancing latent pattern learning and overall discriminative capability.\u00a0<\/jats:p>","DOI":"10.24018\/ejai.2026.5.1.1076","type":"journal-article","created":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T13:03:04Z","timestamp":1770037384000},"page":"23-29","update-policy":"https:\/\/doi.org\/10.24018\/ejai.crossmark","source":"Crossref","is-referenced-by-count":1,"title":["FORCE: Feature-Oriented Representation with Clustering and Explanation"],"prefix":"10.24018","volume":"5","author":[{"given":"Rishav","family":"Mukherjee","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeffrey Ahearn","family":"Thompson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"10105","published-online":{"date-parts":[[2026,1,26]]},"reference":[{"key":"304478","doi-asserted-by":"crossref","unstructured":"Rajkumar A, Hardt M, Howell DM, Corrado G, Chin MH.Ensuring fairness in machine learning to advance health equity. Ann Intern Med. 2018;169(12):866\u201372.","DOI":"10.7326\/M18-1990"},{"key":"304479","doi-asserted-by":"crossref","unstructured":"Azimi R, Ghayekhloo M, Ghofrani M. A hybrid method based on a new clustering technique and multilayer perceptron neural networks for hourly solar radiation forecasting. Energy Convers Manag. 2016;118:331\u201344.","DOI":"10.1016\/j.enconman.2016.04.009"},{"key":"304480","doi-asserted-by":"crossref","unstructured":"G\u00fcr\u00fcler H. A novel diagnosis system for Parkinson\u2019s disease using complex-valued artificial neural network with k-means clustering feature weighting method. Neural Comput Appl. 2017;28:1657\u201366.","DOI":"10.1007\/s00521-015-2142-2"},{"key":"304481","unstructured":"Lundberg SM, Lee SI. A unified approach to interpreting model predictions. Adv Neural Inf Process Syst. 2017;30:4768\u20134777."},{"key":"304482","unstructured":"Molnar C. Interpretable Machine Learning. Lulu. com.; 2020."},{"key":"304483","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, et al. Attention is all you need. In Advances in Neural Information Processing Systems. Curran Associates, Inc., 2017."},{"key":"304484","doi-asserted-by":"crossref","unstructured":"Yang B, Wang L, Wong DF, Shi S, Tu Z. Context-aware self-attention networks for natural language processing. Neurocomputing. 2021;458:157\u201369.","DOI":"10.1016\/j.neucom.2021.06.009"},{"key":"304485","doi-asserted-by":"crossref","unstructured":"Bello I, Zoph B, Vaswani A, Shlens J, Le QV. Attention augmented convolutional networks. IEEE\/CVF International Conference on Computer Vision, 2019.","DOI":"10.1109\/ICCV.2019.00338"},{"key":"304486","doi-asserted-by":"crossref","unstructured":"Natekin A, Knoll A. Gradient boosting machines, a tutorial. Front Neurorobot. 2013;7. https:\/\/www.frontiersin.org\/journals\/neurorobotics\/articles\/10.3389\/fnbot.2013.00021.","DOI":"10.3389\/fnbot.2013.00021"},{"key":"304487","doi-asserted-by":"crossref","unstructured":"Dhillon IS, Guan Y, Kulis B. Kernel k-means: spectral clustering and normalized cuts. Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Seattle, WA, USA: Association for Computing Machinery, 2004, pp. 551\u20136.","DOI":"10.1145\/1014052.1014118"},{"key":"304488","doi-asserted-by":"crossref","unstructured":"Islam MMF, Ferdousi R, Rahman S, Bushra H. Likelihood Prediction of Diabetes at Early Stage Using Data Mining Techniques. Singapore: Springer Singapore; 2020.","DOI":"10.1007\/978-981-13-8798-2_12"},{"key":"304489","doi-asserted-by":"crossref","unstructured":"Tang Y, Ji J, Gao S, Dai H, Yu Y, Todo Y. A pruning neural network model in credit classification analysis. Comput Intell Neurosci. 2018;2018(1):9390410.","DOI":"10.1155\/2018\/9390410"},{"key":"304490","unstructured":"Cooper A. Supervised clustering: how to use SHAP values for better cluster analysis. 2022. Available from: aidencooper.co.uk."},{"key":"304491","doi-asserted-by":"crossref","unstructured":"Wang H, Liang Q, Hancock JT, Khoshgoftaar TM. Feature selection strategies: a comparative analysis of SHAP-value and importance-based methods. J Big Data. 2024;11:44. doi: https:\/\/doi.org\/10.1186\/s40537-024-00905-w.","DOI":"10.1186\/s40537-024-00905-w"},{"key":"304492","doi-asserted-by":"crossref","unstructured":"Hastie T, Tibshirani R, Friedman J. The Elements of Statistical Learning. New York, NY, USA: Springer New York Inc; 2001.","DOI":"10.1007\/978-0-387-21606-5"},{"key":"304493","doi-asserted-by":"crossref","unstructured":"Golinko E, Zhu X. Generalized feature embedding for supervised, unsupervised, and online learning tasks. Inf Syst Front. 2019;21:125\u201342. doi: https:\/\/doi.org\/10.1007\/s10796-018-9850-y.","DOI":"10.1007\/s10796-018-9850-y"},{"key":"304494","doi-asserted-by":"crossref","unstructured":"Sofia Serrano NAS. Is attention interpretable? 2019.","DOI":"10.18653\/v1\/P19-1282"}],"container-title":["European Journal of Artificial Intelligence and Machine Learning"],"original-title":[],"link":[{"URL":"https:\/\/eu-opensci.org\/index.php\/ejai\/article\/download\/1076\/13602","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/eu-opensci.org\/index.php\/ejai\/article\/download\/1076\/13605","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/eu-opensci.org\/index.php\/ejai\/article\/download\/1076\/13604","content-type":"application\/epub+zip","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/eu-opensci.org\/index.php\/ejai\/article\/download\/1076\/13602","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,21]],"date-time":"2026-06-21T14:17:48Z","timestamp":1782051468000},"score":1,"resource":{"primary":{"URL":"https:\/\/eu-opensci.org\/index.php\/ejai\/article\/view\/1076"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,26]]},"references-count":17,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1,4]]}},"URL":"https:\/\/doi.org\/10.24018\/ejai.2026.5.1.1076","relation":{},"ISSN":["2796-0072"],"issn-type":[{"value":"2796-0072","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,26]]}}}