{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T13:19:35Z","timestamp":1767705575079,"version":"build-2065373602"},"reference-count":29,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2023,8,3]],"date-time":"2023-08-03T00:00:00Z","timestamp":1691020800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Office of Dean of the College of Engineering &amp; Applied Science at the University of Wisconsin-Milwaukee"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["MAKE"],"abstract":"<jats:p>Decision support systems based on machine learning models should be able to help users identify opportunities and threats. Popular model-agnostic explanation models can identify factors that support various predictions, answering questions such as \u201cWhat factors affect sales?\u201d or \u201cWhy did sales decline?\u201d, but do not highlight what a person should or could do to get a more desirable outcome. Counterfactual explanation approaches address intervention, and some even consider feasibility, but none consider their suitability for real-time applications, such as question answering. Here, we address this gap by introducing a novel model-agnostic method that provides specific, feasible changes that would impact the outcomes of a complex Black Box AI model for a given instance and assess its real-world utility by measuring its real-time performance and ability to find achievable changes. The method uses the instance of concern to generate high-precision explanations and then applies a secondary method to find achievable minimally-contrastive counterfactual explanations (AMCC) while limiting the search to modifications that satisfy domain-specific constraints. Using a widely recognized dataset, we evaluated the classification task to ascertain the frequency and time required to identify successful counterfactuals. For a 90% accurate classifier, our algorithm identified AMCC explanations in 47% of cases (38 of 81), with an average discovery time of 80 ms. These findings verify the algorithm\u2019s efficiency in swiftly producing AMCC explanations, suitable for real-time systems. The AMCC method enhances the transparency of Black Box AI models, aiding individuals in evaluating remedial strategies or assessing potential outcomes.<\/jats:p>","DOI":"10.3390\/make5030048","type":"journal-article","created":{"date-parts":[[2023,8,3]],"date-time":"2023-08-03T11:35:21Z","timestamp":1691062521000},"page":"922-936","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Achievable Minimally-Contrastive Counterfactual Explanations"],"prefix":"10.3390","volume":"5","author":[{"given":"Hosein","family":"Barzekar","sequence":"first","affiliation":[{"name":"Department of Computer Science, University of Wisconsin-Milwaukee, Milwaukee, WI 53211, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4826-0947","authenticated-orcid":false,"given":"Susan","family":"McRoy","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Wisconsin-Milwaukee, Milwaukee, WI 53211, USA"}]}],"member":"1968","published-online":{"date-parts":[[2023,8,3]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.T., Singh, S., and Guestrin, C. (2016, January 13\u201317). \u201cWhy Should I Trust You?\u201d: Explaining the Predictions of Any Classifier. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD\u201916, San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939778"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"102551","DOI":"10.1016\/j.ijhcs.2020.102551","article-title":"The effects of explainability and causability on perception, trust, and acceptance: Implications for explainable AI","volume":"146","author":"Shin","year":"2021","journal-title":"Int. J. Hum.-Comput. Stud."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.T., Singh, S., and Guestrin, C. (2018, January 2\u20137). Anchors: High-Precision Model-Agnostic Explanations. Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), New Orleans, LA, USA.","DOI":"10.1609\/aaai.v32i1.11491"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1207\/S15327965PLI1104_01","article-title":"The\u201cwhat\u201d and\u201c why\u201d of goal pursuits: Human needs and the self-determination of behavior","volume":"11","author":"Deci","year":"2000","journal-title":"Psychol. Inq."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1037\/0003-066X.55.1.68","article-title":"Self-determination theory and the facilitation of intrinsic motivation, social development, and well-being","volume":"55","author":"Ryan","year":"2000","journal-title":"Am. Psychol."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1016\/bs.adms.2019.01.001","article-title":"Brick by brick: The origins, development, and future of self-determination theory","volume":"Volume 6","author":"Ryan","year":"2019","journal-title":"Advances in Motivation Science"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1080\/17437199.2016.1151372","article-title":"Theoretical explanations for maintenance of behaviour change: A systematic review of behaviour theories","volume":"10","author":"Kwasnicka","year":"2016","journal-title":"Health Psychol. Rev."},{"key":"ref_8","first-page":"35","article-title":"There\u2019s a SMART way to write management\u2019s goals and objectives","volume":"70","author":"Doran","year":"1981","journal-title":"Manag. Rev."},{"key":"ref_9","first-page":"83","article-title":"Using Technology to Help Students Set, Monitor, and Achieve Goals","volume":"3","author":"Burik","year":"2021","journal-title":"Adult Lit. Educ."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Gupta, A., Basu, D., Ghantasala, R., Qiu, S., and Gadiraju, U. (2022, January 25\u201329). To trust or not to trust: How a conversational interface affects trust in a decision support system. Proceedings of the ACM Web Conference 2022, Lyon, France.","DOI":"10.1145\/3485447.3512248"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Mittelstadt, B., Russell, C., and Wachter, S. (2019, January 29\u201331). Explaining explanations in AI. Proceedings of the Conference on Fairness, Accountability, and Transparency, Atlanta, GA, USA.","DOI":"10.1145\/3287560.3287574"},{"key":"ref_12","unstructured":"Ku\u017aba, M., and Biecek, P. (2020, January 14\u201318). What would you ask the machine learning model? Identification of user needs for model explanations based on human-model conversations. Proceedings of the ECML PKDD 2020 Workshops: Workshops of the European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD 2020): SoGood 2020, PDFL 2020, MLCS 2020, NFMCP 2020, DINA 2020, EDML 2020, XKDD 2020 and INRA 2020, Ghent, Belgium."},{"key":"ref_13","first-page":"841","article-title":"Counterfactual explanations without opening the black box: Automated decisions and the GDPR","volume":"31","author":"Wachter","year":"2017","journal-title":"Harv. JL Tech."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"11974","DOI":"10.1109\/ACCESS.2021.3051315","article-title":"A survey of contrastive and counterfactual explanation generation methods for explainable artificial intelligence","volume":"9","author":"Stepin","year":"2021","journal-title":"IEEE Access"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Karimi, A.H., Sch\u00f6lkopf, B., and Valera, I. (2021, January 3\u201310). Algorithmic recourse: From counterfactual explanations to interventions. Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency, Toronto, ON, Canada.","DOI":"10.1145\/3442188.3445899"},{"key":"ref_16","first-page":"265","article-title":"Algorithmic recourse under imperfect causal knowledge: A probabilistic approach","volume":"33","author":"Karimi","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_17","unstructured":"Kaddour, J., Lynch, A., Liu, Q., Kusner, M.J., and Silva, R. (2022). Causal Machine Learning: A Survey and Open Problems. arXiv."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"555","DOI":"10.1016\/j.intcom.2011.05.008","article-title":"40 years of searching for the best computer system response time","volume":"23","author":"Dabrowski","year":"2011","journal-title":"Interact. Comput."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1353","DOI":"10.1108\/INTR-05-2019-0223","article-title":"Unravelling the relationship between response time and user experience in mobile applications","volume":"30","author":"Yu","year":"2020","journal-title":"Internet Res."},{"key":"ref_20","unstructured":"Lundberg, S.M., and Lee, S.I. (2017). A unified approach to interpreting model predictions. Adv. Neural Inf. Process. Syst., 30."},{"key":"ref_21","unstructured":"Rathi, S. (2019). Generating counterfactual and contrastive explanations using SHAP. arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"977","DOI":"10.1111\/cogs.12065","article-title":"Structural counterfactuals: A brief introduction","volume":"37","author":"Pearl","year":"2013","journal-title":"Cogn. Sci."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Poyiadzi, R., Sokol, K., Santos-Rodriguez, R., De Bie, T., and Flach, P. (2020, January 7\u20138). FACE: Feasible and actionable counterfactual explanations. Proceedings of the AAAI\/ACM Conference on AI, Ethics, and Society, New York, NY, USA.","DOI":"10.1145\/3375627.3375850"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Ustun, B., Spangher, A., and Liu, Y. (2019, January 29\u201331). Actionable recourse in linear classification. Proceedings of the Conference on Fairness, Accountability, and Transparency, Atlanta, GA, USA.","DOI":"10.1145\/3287560.3287566"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Mothilal, R.K., Sharma, A., and Tan, C. (2020, January 27\u201330). Explaining machine learning classifiers through diverse counterfactual explanations. Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, Barcelona, Spain.","DOI":"10.1145\/3351095.3372850"},{"key":"ref_26","unstructured":"Murphy, K.P. (2022). Probabilistic Machine Learning: An Introduction, MIT Press."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3447772","article-title":"Knowledge graphs","volume":"54","author":"Hogan","year":"2021","journal-title":"ACM Comput. Surv. (Csur)"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Kimani, E., Rowan, K., McDuff, D., Czerwinski, M., and Mark, G. (2019, January 3\u20136). A conversational agent in support of productivity and wellbeing at work. Proceedings of the 2019 8th International Conference on Affective Computing and Intelligent Interaction (ACII), Cambridge, UK.","DOI":"10.1109\/ACII.2019.8925488"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"e22845","DOI":"10.2196\/22845","article-title":"Artificial intelligence chatbot behavior change model for designing artificial intelligence chatbots to promote physical activity and a healthy diet","volume":"22","author":"Zhang","year":"2020","journal-title":"J. Med. Internet Res."}],"container-title":["Machine Learning and Knowledge Extraction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-4990\/5\/3\/48\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T20:25:13Z","timestamp":1760127913000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-4990\/5\/3\/48"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,3]]},"references-count":29,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2023,9]]}},"alternative-id":["make5030048"],"URL":"https:\/\/doi.org\/10.3390\/make5030048","relation":{},"ISSN":["2504-4990"],"issn-type":[{"type":"electronic","value":"2504-4990"}],"subject":[],"published":{"date-parts":[[2023,8,3]]}}}