{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,15]],"date-time":"2025-04-15T01:10:07Z","timestamp":1744679407371,"version":"3.40.4"},"reference-count":24,"publisher":"American Institute of Mathematical Sciences (AIMS)","issue":"4","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["era"],"published-print":{"date-parts":[[2025]]},"DOI":"10.3934\/era.2025092","type":"journal-article","created":{"date-parts":[[2025,4,15]],"date-time":"2025-04-15T00:46:16Z","timestamp":1744677976000},"page":"2092-2117","source":"Crossref","is-referenced-by-count":0,"title":["Striking a balance: navigating the trade-offs between predictive accuracy and interpretability in machine learning models"],"prefix":"10.3934","volume":"33","author":[{"given":"Miguel","family":"Arantes","sequence":"first","affiliation":[]},{"name":"Departamento de Matem\u00e1tica, Faculdade de Ci\u00eancias da Universidade do Porto, Porto 4785-999, Portugal","sequence":"first","affiliation":[]},{"given":"Wenceslao","family":"Gonz\u00e1lez-Manteiga","sequence":"additional","affiliation":[]},{"given":"Javier","family":"Torres","sequence":"additional","affiliation":[]},{"given":"Alberto","family":"Pinto","sequence":"additional","affiliation":[]},{"name":"Departamento de Estad\u00edstica, An\u00e1lisis Matem\u00e1tico y Optimizaci\u00f3n, Universidad de Santiago de Compostela, Santigo de Compostela, Spain","sequence":"additional","affiliation":[]},{"name":"CITMAga: Centro de Investigaci\u00f3n e Tecnolox\u00eda Matem\u00e1tica de Galicia, Santiago de Compostela, Spain","sequence":"additional","affiliation":[]},{"name":"Departamento de Matem\u00e1tica Aplicada, Universidad de Vigo, Vigo 28039, Spain","sequence":"additional","affiliation":[]},{"name":"LIAAD - INESC TEC, Porto 4785-999, Portugal","sequence":"additional","affiliation":[]}],"member":"2321","reference":[{"key":"key-10.3934\/era.2025092-1","doi-asserted-by":"publisher","unstructured":"S. Hochreiter, J. Schmidhuber, Long short-term memory, <i>Neural Comput.<\/i>, <b>9<\/b> (1997), 1735\u20131780. http:\/\/dx.doi.org\/10.1162\/neco.1997.9.8.1735","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"key-10.3934\/era.2025092-2","doi-asserted-by":"publisher","unstructured":"R. Roscher, B. Bohn, M. F. Duarte, J. Garcke, Explainable machine learning for scientific insights and discoveries, <i>IEEE Access<\/i>, <b>8<\/b> (2020), 40200\u201340216. https:\/\/doi.org\/10.1109\/ACCESS.2020.2976199","DOI":"10.1109\/ACCESS.2020.2976199"},{"key":"key-10.3934\/era.2025092-3","unstructured":"F. Giannotti, F. Naretto, F, Bodria, Explainable for trustworthy AI, in <i>Human-Centered Artificial Intelligence<\/i>, (eds. M. Chetouani, V. Dignum, P. Lukowicz and C. Sierra), Springer, Lecture Notes in Computer Science, (2023), 175\u2013195. <ext-link ext-link-type=\"uri\" xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/doi.org\/10.1007\/978-3-031-24349-3_10\">https:\/\/doi.org\/10.1007\/978-3-031-24349-3_10<\/ext-link>"},{"key":"key-10.3934\/era.2025092-4","doi-asserted-by":"publisher","unstructured":"A. Barredo-Arrieta, N. D\u00edaz-Rodr\u00edguez, J. Del Ser, A. Bennetot, S. Tabik, A. Barbado, et al., Explainable artificial intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI, <i>Inf. Fusion<\/i>, <b>58<\/b> (2020), 82\u2013115. https:\/\/doi.org\/10.1016\/j.inffus.2019.12.012","DOI":"10.1016\/j.inffus.2019.12.012"},{"key":"key-10.3934\/era.2025092-5","doi-asserted-by":"publisher","unstructured":"X. Dastile, T. Celik, Making deep learning-based predictions for credit scoring interpretable, <i>IEEE Access<\/i>, <b>9<\/b> (2021), 50426\u201350440. http:\/\/dx.doi.org\/10.1109\/ACCESS.2021.3068854","DOI":"10.1109\/ACCESS.2021.3068854"},{"key":"key-10.3934\/era.2025092-6","doi-asserted-by":"publisher","unstructured":"S. Taylor, B. Letham, Forecasting at scale, <i>Am. Stat.<\/i>, <b>72<\/b> (2018), 37\u201345. https:\/\/doi.org\/10.1109\/ITSC.2019.8916985","DOI":"10.1109\/ITSC.2019.8916985"},{"key":"key-10.3934\/era.2025092-7","unstructured":"<i>Proposal for a Regulation of the European Parliament and of the Council laying down harmonised rules on Artificial Intelligence (Artificial Intelligence Act) and amending certain Union legislative acts<\/i>, European Commission, 2021."},{"key":"key-10.3934\/era.2025092-8","doi-asserted-by":"publisher","unstructured":"L. Bohlen, J. Rosenberger, P. Zschech, M. Kraus, Leveraging interpretable machine learning in intensive care, <i>Ann. Oper. Res.<\/i>, (2024), 1\u201340. http:\/\/dx.doi.org\/10.1007\/s10479-024-06226-8","DOI":"10.1007\/s10479-024-06226-8"},{"key":"key-10.3934\/era.2025092-9","unstructured":"D. Alvarez-Melis, T. Jaakkola, On the robustness of interpretability methods, preprint, arXiv: 1806.08049. <ext-link ext-link-type=\"uri\" xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/doi.org\/10.48550\/arXiv.1806.08049\">https:\/\/doi.org\/10.48550\/arXiv.1806.08049<\/ext-link>"},{"key":"key-10.3934\/era.2025092-10","unstructured":"Y. Yang, M. Wu, Explainable machine learning for improving logistic regression models, in <i>2021 IEEE 19th International Conference on Industrial Informatics (INDIN)<\/i>, (2021), 1\u20136. <ext-link ext-link-type=\"uri\" xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/doi.org\/10.1109\/INDIN45523.2021.9557392\">https:\/\/doi.org\/10.1109\/INDIN45523.2021.9557392<\/ext-link>"},{"key":"key-10.3934\/era.2025092-11","doi-asserted-by":"publisher","unstructured":"D. Gunning, D. W. Aha, DARPA's explainable artificial intelligence (XAI) program, <i>AI Mag.<\/i>, <b>40<\/b> (2019), 44\u201358. https:\/\/doi.org\/10.1609\/aimag.v40i2.2850","DOI":"10.1609\/aimag.v40i2.2850"},{"key":"key-10.3934\/era.2025092-12","doi-asserted-by":"publisher","unstructured":"S. M. Lundberg, G. Erion, H. Chen, A. DeGrave, J. M. Prutkin, B. Nair, et al., From local explanations to global understanding with explainable AI for trees, <i>Nat. Mach. Intell.<\/i>, <b>2<\/b> (2020), 56\u201367. https:\/\/doi.org\/10.1007\/s42979-021-00815-1","DOI":"10.1007\/s42979-021-00815-1"},{"key":"key-10.3934\/era.2025092-13","doi-asserted-by":"publisher","unstructured":"J. Hu, K. Zhu, S. Cheng, N. M. Kovalchuk, A. Soulsby, M. J. H. Simmons, et al., Explainable AI models for predicting drop coalescence in microfluidics device, <i>Chem. Eng. J.<\/i>, <b>481<\/b> (2024), 148465. https:\/\/doi.org\/10.1016\/j.cej.2023.148465","DOI":"10.1016\/j.cej.2023.148465"},{"key":"key-10.3934\/era.2025092-14","doi-asserted-by":"publisher","unstructured":"C. Xie, J. Hu, G. Vasdravellis, X. Wang, S. Cheng, Explainable AI model for predicting equivalent viscous damping in dual frame\u2013wall resilient system, <i>J. Build. Eng.<\/i>, <b>96<\/b> (2024), 110564. https:\/\/doi.org\/10.1016\/j.jobe.2024.110564","DOI":"10.1016\/j.jobe.2024.110564"},{"key":"key-10.3934\/era.2025092-15","doi-asserted-by":"crossref","unstructured":"A. Barredo-Arrieta, I. Lana, J. Del Ser, What lies beneath: A note on the explainability of black-box machine learning models for road traffic forecasting, in <i>2019 IEEE Intelligent Transportation Systems Conference (ITSC)<\/i>, (2019), 2232\u20132237. <ext-link ext-link-type=\"uri\" xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/doi.org\/10.1109\/ITSC.2019.8916985\">https:\/\/doi.org\/10.1109\/ITSC.2019.8916985<\/ext-link>","DOI":"10.1109\/ITSC.2019.8916985"},{"key":"key-10.3934\/era.2025092-16","unstructured":"L. S. Shapley, A value for n-person games, in <i>Contributions to the Theory of Games, Volume II<\/i>, (eds. Harold W. Kuhn and Albert William Tucker), Princeton University Press, (1953), 307\u2013318. <ext-link ext-link-type=\"uri\" xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/doi.org\/10.1515\/9781400881970-018\">https:\/\/doi.org\/10.1515\/9781400881970-018<\/ext-link>"},{"key":"key-10.3934\/era.2025092-17","doi-asserted-by":"publisher","unstructured":"A. Rawal, J. McCoy, D. B. Rawat, B. M. Sadler, R. S. Amant, Recent advances in trustworthy explainable artificial intelligence: Status, challenges, and perspectives, <i>IEEE Trans. Artif. Intell.<\/i>, <b>3<\/b> (2022), 852\u2013866. https:\/\/doi.org\/10.1109\/TAI.2021.3133846","DOI":"10.1109\/TAI.2021.3133846"},{"key":"key-10.3934\/era.2025092-18","unstructured":"C. Bove, T. Laugel, M. J. Lesot, C. Tijus, M. Detyniecki, Why do explanations fail? A typology and discussion on failures in XAI, preprint, arXiv: 2405.13474. <ext-link ext-link-type=\"uri\" xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/doi.org\/10.48550\/arXiv.2405.13474\">https:\/\/doi.org\/10.48550\/arXiv.2405.13474<\/ext-link>"},{"key":"key-10.3934\/era.2025092-19","unstructured":"S. Wachter, B. Mittelstadt, C. Russel, Counterfactual explanations without opening the black box: Automated decisions and the GDPR, preprint, arXiv: 1711.00399. <ext-link ext-link-type=\"uri\" xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"http:\/\/dx.doi.org\/10.48550\/arXiv.1711.00399\">http:\/\/dx.doi.org\/10.48550\/arXiv.1711.00399<\/ext-link>"},{"key":"key-10.3934\/era.2025092-20","doi-asserted-by":"publisher","unstructured":"I. H. Sarke, Deep learning: A comprehensive overview on techniques, taxonomy, applications and research directions, <i>SN Comput. Sci.<\/i>, <b>2<\/b> (2021), 420. https:\/\/doi.org\/10.1007\/s42979-021-00815-1","DOI":"10.1007\/s42979-021-00815-1"},{"key":"key-10.3934\/era.2025092-21","unstructured":"Z. C. Lipton, The Mythos of model interpretability: In machine learning, the concept of interpretability is both important and slippery, preprint, arXiv: 1606.03490. <ext-link ext-link-type=\"uri\" xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/doi.org\/10.48550\/arXiv.1606.03490\">https:\/\/doi.org\/10.48550\/arXiv.1606.03490<\/ext-link>"},{"key":"key-10.3934\/era.2025092-22","doi-asserted-by":"publisher","unstructured":"G. Van Houdt, C. Mosquera, G. N\u00e1poles, A review on the long short-term memory model, <i>Artif. Intell. Rev.<\/i>, <b>53<\/b> (2020), 5929\u20135955. https:\/\/doi.org\/10.1007\/s10462-020-09838-1","DOI":"10.1007\/s10462-020-09838-1"},{"key":"key-10.3934\/era.2025092-23","unstructured":"P. Biecek, M. Chlebus, J. Gajda, A. Gosiewska, A. Kozak, D. Ogonowski, et al., Enabling machine learning algorithms for credit scoring, preprint, preprint, arXiv: 2104.06735."},{"key":"key-10.3934\/era.2025092-24","doi-asserted-by":"publisher","unstructured":"C. Zhang, P. Hoes, S. Wang, Y. Zhao, Intrinsically interpretable machine learning-based building energy load prediction method with high accuracy and strong interpretability, <i>Energy Built Environ.<\/i>, <b>5<\/b> (2024). https:\/\/doi.org\/10.1016\/j.enbenv.2024.08.006","DOI":"10.1016\/j.enbenv.2024.08.006"}],"container-title":["Electronic Research Archive"],"original-title":[],"link":[{"URL":"http:\/\/www.aimspress.com\/article\/doi\/10.3934\/era.2025092?viewType=html","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,15]],"date-time":"2025-04-15T00:46:19Z","timestamp":1744677979000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.aimspress.com\/article\/doi\/10.3934\/era.2025092"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":24,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.3934\/era.2025092","relation":{},"ISSN":["2688-1594"],"issn-type":[{"value":"2688-1594","type":"print"}],"subject":[],"published":{"date-parts":[[2025]]}}}