{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T07:14:44Z","timestamp":1779174884211,"version":"3.51.4"},"reference-count":47,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2023,12,8]],"date-time":"2023-12-08T00:00:00Z","timestamp":1701993600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. ACM Manag. Data"],"published-print":{"date-parts":[[2023,12,8]]},"abstract":"<jats:p>Machine learning systems are deployed in domains such as hiring and healthcare, where undesired classifications can have serious ramifications for the user. Thus, there is a rising demand for explainable AI systems which provide actionable steps for lay users to obtain their desired outcome. To meet this need, we propose FACET, the first explanation analytics system which supports a user in interactively refining counterfactual explanations for decisions made by tree ensembles. As FACET's foundation, we design a novel type of counterfactual explanation called the counterfactual region. Unlike traditional counterfactuals, FACET's regions concisely describe portions of the feature space where the desired outcome is guaranteed, regardless of variations in exact feature values. This property, which we coin explanation robustness, is critical for the practical application of counterfactuals. We develop a rich set of novel explanation analytics queries which empower users to identify personalized counterfactual regions that account for their real-world circumstances. To process these queries, we develop a compact high-dimensional counterfactual region index along with index-aware query processing strategies for near real-time explanation analytics. We evaluate FACET against state-of-the-art explanation techniques on eight public benchmark datasets and demonstrate that FACET generates actionable explanations of similar quality in an order of magnitude less time while providing critical robustness guarantees. Finally, we conduct a preliminary user study which suggests that FACET's regions lead to higher user understanding than traditional counterfactuals.<\/jats:p>","DOI":"10.1145\/3626729","type":"journal-article","created":{"date-parts":[[2023,12,12]],"date-time":"2023-12-12T14:01:21Z","timestamp":1702389681000},"page":"1-27","source":"Crossref","is-referenced-by-count":11,"title":["FACET: Robust Counterfactual Explanation Analytics"],"prefix":"10.1145","volume":"1","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0285-6019","authenticated-orcid":false,"given":"Peter M.","family":"VanNostrand","sequence":"first","affiliation":[{"name":"Worcester Polytechnic Institute, Worcester, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8547-2483","authenticated-orcid":false,"given":"Huayi","family":"Zhang","sequence":"additional","affiliation":[{"name":"ByteDance &amp; Worcester Polytechnic Institute, San Jose, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8102-3081","authenticated-orcid":false,"given":"Dennis M.","family":"Hofmann","sequence":"additional","affiliation":[{"name":"Worcester Polytechnic Institute, Worcester, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5375-9254","authenticated-orcid":false,"given":"Elke A.","family":"Rundensteiner","sequence":"additional","affiliation":[{"name":"Worcester Polytechnic Institute, Worcester, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,12,12]]},"reference":[{"key":"e_1_2_2_1_1","unstructured":"Equal Credit Opportunities Act. 1974. Public Law 15 C.F.R \u00a7 1691 Regulation B 12 C.F.R. \u00a7 1002."},{"key":"e_1_2_2_2_1","volume-title":"Peeking inside the black-box: a survey on explainable artificial intelligence (XAI)","author":"Adadi Amina","year":"2018","unstructured":"Amina Adadi and Mohammed Berrada. 2018. Peeking inside the black-box: a survey on explainable artificial intelligence (XAI). IEEE access, Vol. 6 (2018), 52138--52160."},{"key":"e_1_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3372830"},{"key":"e_1_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/93597.98741"},{"key":"e_1_2_2_5_1","volume-title":"Proceedings of the Twenty-second International Conference on Very Large Data-Bases ; Mumbai (Bombay), India 3 -","author":"Berchtold Stefan","year":"1996","unstructured":"Stefan Berchtold, Daniel A. Keim, and Hans-Peter Kriegel. 1996. The X-Tree : An Index Structure for High-Dimensional Data. In Proceedings of the Twenty-second International Conference on Very Large Data-Bases ; Mumbai (Bombay), India 3 - 6 September, 1996, T. M. Vijayaraman (Ed.). Morgan Kaufmann, San Francisco, 28--39."},{"key":"e_1_2_2_6_1","unstructured":"Erik Bernhardsson. 2005. Spotify\/Annoy: Approximate nearest neighbors in c\/python optimized for memory usage and loading\/saving to disk. https:\/\/github.com\/spotify\/annoy."},{"key":"e_1_2_2_7_1","volume-title":"2001 a. Random forests. Machine learning","author":"Breiman Leo","year":"2001","unstructured":"Leo Breiman. 2001 a. Random forests. Machine learning, Vol. 45, 1 (2001), 5--32."},{"key":"e_1_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1214\/ss\/1009213726"},{"key":"e_1_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783281"},{"key":"e_1_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41060-018-0144-8"},{"key":"e_1_2_2_11_1","volume-title":"Advances in Neural Information Processing Systems","author":"Dhurandhar Amit","year":"2018","unstructured":"Amit Dhurandhar, Pin-Yu Chen, Ronny Luss, Chun-Chen Tu, Paishun Ting, Karthikeyan Shanmugam, and Payel Das. 2018. Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives. In Advances in Neural Information Processing Systems, S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi, and R. Garnett (Eds.), Vol. 31. Curran Associates, Inc., Montreal, QC, Canada, 12. https:\/\/proceedings.neurips.cc\/paper\/2018\/file\/c5ff2543b53f4cc0ad3819a36752467b-Paper.pdf"},{"key":"e_1_2_2_12_1","volume-title":"Model Agnostic Contrastive Explanations for Structured Data. ArXiv preprint","author":"Dhurandhar Amit","year":"2019","unstructured":"Amit Dhurandhar, Tejaswini Pedapati, Avinash Balakrishnan, Pin-Yu Chen, Karthikeyan Shanmugam, and Ruchir Puri. 2019. Model Agnostic Contrastive Explanations for Structured Data. ArXiv preprint, Vol. abs\/1906.00117 (2019), 12 pages. https:\/\/arxiv.org\/abs\/1906.00117"},{"key":"e_1_2_2_13_1","unstructured":"Wei Dong. 2014. AAALGO\/kgraph: A library for K-Nearest Neighbor Search. https:\/\/github.com\/aaalgo\/kgraph."},{"key":"e_1_2_2_14_1","unstructured":"Dheeru Dua and Casey Graff. 2017. UCI Machine Learning Repository. http:\/\/archive.ics.uci.edu\/ml"},{"key":"e_1_2_2_15_1","volume-title":"Proceedings of the 39th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"5756","author":"Dutta Sanghamitra","year":"2022","unstructured":"Sanghamitra Dutta, Jason Long, Saumitra Mishra, Cecilia Tilli, and Daniele Magazzeni. 2022. Robust Counterfactual Explanations for Tree-Based Ensembles. In Proceedings of the 39th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 162), Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesvari, Gang Niu, and Sivan Sabato (Eds.). PMLR, Baltimore, MD, USA, 5742--5756. https:\/\/proceedings.mlr.press\/v162\/dutta22a.html"},{"key":"e_1_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.07.001"},{"key":"e_1_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3458455"},{"key":"e_1_2_2_18_1","volume-title":"Local Rule-Based Explanations of Black Box Decision Systems. CoRR","author":"Guidotti Riccardo","year":"2018","unstructured":"Riccardo Guidotti, Anna Monreale, Salvatore Ruggieri, Dino Pedreschi, Franco Turini, and Fosca Giannotti. 2018. Local Rule-Based Explanations of Black Box Decision Systems. CoRR, Vol. abs\/1805.10820 (2018), 10 pages.showeprint[arXiv]1805.10820 http:\/\/arxiv.org\/abs\/1805.10820"},{"key":"e_1_2_2_19_1","doi-asserted-by":"publisher","unstructured":"Masoud Hashemi and Ali Fathi. 2020. PermuteAttack: Counterfactual Explanation of Machine Learning Credit Scorecards. https:\/\/doi.org\/10.48550\/ARXIV.2008.10138","DOI":"10.48550\/ARXIV.2008.10138"},{"key":"e_1_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.14778\/2850469.2850470"},{"key":"e_1_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1979.4766900"},{"key":"e_1_2_2_22_1","volume-title":"Twenty-fourth International Joint Conference on Artificial Intelligence. AAAI","author":"Jiang Qing-Yuan","year":"2015","unstructured":"Qing-Yuan Jiang and Wu-Jun Li. 2015. Scalable graph hashing with feature transformation. In Twenty-fourth International Joint Conference on Artificial Intelligence. AAAI, Buenos Aires, Argentina, 2248--2254."},{"key":"e_1_2_2_23_1","unstructured":"Kaggle. 2008. Loan Predication. https:\/\/www.kaggle.com\/datasets\/ninzaami\/loan-predication ."},{"key":"e_1_2_2_24_1","volume-title":"Hilbert R-tree: An improved R-tree using fractals. Technical Report","author":"Kamel Ibrahim","year":"1993","unstructured":"Ibrahim Kamel and Christos Faloutsos. 1993. Hilbert R-tree: An improved R-tree using fractals. Technical Report. University of Maryland, Institute for Systems Research."},{"key":"e_1_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/395"},{"key":"e_1_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3527848"},{"key":"e_1_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445899"},{"key":"e_1_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403066"},{"key":"e_1_2_2_29_1","unstructured":"Scikit Learn. 2023. Gradient Boosting Classifier. https:\/\/scikit-learn.org\/stable\/modules\/generated\/sklearn.ensemble.GradientBoostingClassifier.html ."},{"key":"e_1_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2014.2346452"},{"key":"e_1_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i5.20468"},{"key":"e_1_2_2_32_1","volume-title":"Advances in Neural Information Processing Systems","author":"Lundberg Scott M","year":"2017","unstructured":"Scott M Lundberg and Su-In Lee. 2017. A Unified Approach to Interpreting Model Predictions. In Advances in Neural Information Processing Systems, I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30. Curran Associates, Inc., Long Beach, CA, USA. https:\/\/proceedings.neurips.cc\/paper\/2017\/file\/8a20a8621978632d76c43dfd28b67767-Paper.pdf"},{"key":"e_1_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2013.10.006"},{"key":"e_1_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2018.07.007"},{"key":"e_1_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3372850"},{"key":"e_1_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2321376"},{"key":"e_1_2_2_37_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"8431","author":"Parmentier Axel","year":"2021","unstructured":"Axel Parmentier and Thibaut Vidal. 2021. Optimal Counterfactual Explanations in Tree Ensembles. In Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, Virtual, 8422--8431. https:\/\/proceedings.mlr.press\/v139\/parmentier21a.html"},{"key":"e_1_2_2_38_1","unstructured":"Article 29 Data Protection Working Party. 2016. Guidelines on Automated Individual Decision-Making and Profiling for the Purposes of Regulation 2016\/679. https:\/\/ec.europa.eu\/newsroom\/article29\/items\/612053"},{"key":"e_1_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2078195"},{"key":"e_1_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3375627.3375850"},{"key":"e_1_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939778"},{"key":"e_1_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.03.013"},{"key":"e_1_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.14778\/3461535.3461555"},{"key":"e_1_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3375627.3375812"},{"key":"e_1_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098039"},{"key":"e_1_2_2_46_1","doi-asserted-by":"publisher","unstructured":"Sahil Verma Varich Boonsanong Minh Hoang Keegan E. Hines John P. Dickerson and Chirag Shah. 2020. Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A Review. https:\/\/doi.org\/10.48550\/ARXIV.2010.10596","DOI":"10.48550\/ARXIV.2010.10596"},{"key":"e_1_2_2_47_1","volume-title":"Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR. Harvard journal of law & technology","author":"Wachter Sandra","year":"2017","unstructured":"Sandra Wachter, Brent Mittelstadt, and Chris Russell. 2017. Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR. Harvard journal of law & technology, Vol. 31, 2 (2017), 841--."}],"container-title":["Proceedings of the ACM on Management of Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626729","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3626729","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T13:01:30Z","timestamp":1755867690000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626729"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,8]]},"references-count":47,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,12,8]]}},"alternative-id":["10.1145\/3626729"],"URL":"https:\/\/doi.org\/10.1145\/3626729","relation":{},"ISSN":["2836-6573"],"issn-type":[{"value":"2836-6573","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,8]]}}}