{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T21:51:25Z","timestamp":1784843485835,"version":"3.55.0"},"reference-count":49,"publisher":"Institute for Operations Research and the Management Sciences (INFORMS)","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Transportation Science"],"published-print":{"date-parts":[[2026,3]]},"abstract":"<jats:p>Airlines take a variety of actions to recover schedules of their aircraft, crew, and passengers from operational disruptions. Aircraft are typically recovered first, followed by crew recovery, and then passenger recovery. This paper aims to repair disrupted crew schedules while ensuring the feasibility of previously decided aircraft recovery plans and indirectly accounting for passenger disruption costs. We develop a fast solution approach that effectively combines mixed-integer optimization and supervised machine learning (ML) methods to find high-quality solutions to large-scale recovery problems. Our approach reduces the solution space by adding constraints based on the patterns discovered in the solutions to offline instances. The model with the added constraints is solved using a mixed-integer optimization solver. To account for the fact that the available time for airlines to handle disruptions may vary during the day of operations, our solution approach allows parameter tuning to flexibly match the extent of solution space reduction to the available runtime. This helps the proposed method to effectively navigate the trade-off between solution quality and runtime. Extensive computational experiments with actual flight and crew schedules of a major U.S. airline with more than 2,800 daily flights show that our approach consistently generates solutions of significantly higher quality than benchmarks and is estimated to provide tens of millions of dollars of reduction in annual operating costs. Moreover, our ML models have interpretable structures that are critical to enhance end-user trust in the ML recommendations. Finally, our approach yields solutions that are more robust to uncertainty in delay prediction than those found by direct optimization.<\/jats:p>\n                  <jats:p>Supplemental Material: The online appendix is available at https:\/\/doi.org\/10.1287\/trsc.2025.0105 .<\/jats:p>","DOI":"10.1287\/trsc.2025.0105","type":"journal-article","created":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T17:16:35Z","timestamp":1766510195000},"page":"177-196","source":"Crossref","is-referenced-by-count":1,"title":["Large-Scale Airline Crew Recovery Using Mixed-Integer Optimization and Supervised Machine Learning"],"prefix":"10.1287","volume":"60","author":[{"given":"Ahmet Esat","family":"H\u0131z\u0131r","sequence":"first","affiliation":[{"name":"Turkish Technology, Istanbul 34696, T\u00fcrkiye; and Massachusetts Institute of Technology, Cambridge, Massachusetts 02139"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cynthia","family":"Barnhart","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology, Cambridge, Massachusetts 02139"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8142-2461","authenticated-orcid":false,"given":"Vikrant","family":"Vaze","sequence":"additional","affiliation":[{"name":"Thayer School of Engineering, Dartmouth College, Hanover, New Hampshire 03755"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"109","reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1023\/B:ANOR.0000019094.19940.41"},{"key":"B2","unstructured":"Alabi D, Kalai AT, Liggett K, Musco C, Tzamos C, Vitercik E (2019) Learning to prune: Speeding up repeated computations. Beygelzimer A, Hsu D, eds.\n                      Proc. 32nd Conf. Learn. Theory\n                      (PMLR, New York), 30\u201333."},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.2016.0723"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1147\/sj.311.0071"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1287\/trsc.2019.0897"},{"key":"B6","unstructured":"Balcan MF, Dick T, Sandholm T, Vitercik E (2018) Learning to branch. Dy J, Krause A, eds.\n                      Proc. 35th Internat. Conf. Machine Learn.\n                      (PMLR, New York), 344\u2013353."},{"key":"B7","unstructured":"Ball M, Barnhart C, Dresner M, Hansen M, Neels K, Odoni A, Peterson E, et al. (2010) Total delay impact study.\n                      NEXTOR Res. Sympos.\n                      (NEXTOR, College Park, MD), 1\u201389."},{"key":"B8","unstructured":"Baltean-Lugojan R, Bonami P, Misener R, Tramontani A (2018) Selecting cutting planes for quadratic semidefinite outer-approximation via trained neural networks. Optimization Online, https:\/\/optimization-online.org\/wp-content\/uploads\/2018\/11\/6943.pdf."},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-1608-1"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1287\/opre.46.3.316"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2020.07.063"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.2022.1181"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"B14","unstructured":"BTS (2020) Airline on-time performance data. Accessed March 15, 2025, https:\/\/www.transtats.bts.gov."},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1287\/trsc.2022.1174"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2016.2560130"},{"key":"B17","doi-asserted-by":"crossref","unstructured":"Chen T, Guestrin C (2016) XGBoost: A scalable tree boosting system.\n                      KDD \u201916: Proc. 22nd ACM SIGKDD Internat. Conf. Knowledge Discovery and Data Mining\n                      (ACM, New York), 785\u2013794.","DOI":"10.1145\/2939672.2939785"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1016\/S0969-6997(98)00012-X"},{"key":"B19","unstructured":"Desrosiers J, Dumas Y, Desrochers M, Soumis F, Sans\u00f2 B, Trudeau P (1991) A breakthrough in airline crew scheduling. Technical report G-91-11, Groupe d\u2019\u00e9tudes et de recherche en analyse des d\u00e9cisions (GERAD), Montr\u00e9al."},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1016\/j.tre.2023.103295"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1007\/s00291-020-00615-8"},{"key":"B22","unstructured":"Gasse M, Chetelat D, Ferroni N, Charlin L, Lodi A (2019) Exact combinatorial optimization with graph convolutional neural networks. Wallach H, Larochelle H, Beygelzimer A, d\u2019Alch\u00e9-Buc F, Fox E, Garnett R, eds.\n                      Proc. 33rd Conf. Neural Inform. Processing Systems (NeurIPS 2019)\n                      (NeurIPS, Vancouver), 15554\u201315566."},{"key":"B23","unstructured":"Gurobi Optimization Inc. (2020) Gurobi optimizer reference manual. Accessed March 15, 2025, https:\/\/www.gurobi.com\/documentation\/current\/refman\/index.html."},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2020.105137"},{"key":"B25","unstructured":"IATA (2023) Net profit of commercial airlines worldwide from 2006 to 2021 and with a forecast until 2023. Accessed March 15, 2025, https:\/\/www.statista.com\/statistics\/232513\/net-profit-of-commercial-airlines-worldwide\/."},{"key":"B26","unstructured":"Interpretable AI (2020) Interpretable AI documentation. Accessed March 15, 2025, https:\/\/docs.interpretable.ai."},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1287\/trsc.1050.0134"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1287\/trsc.2020.0983"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1287\/trsc.34.4.337.12316"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2018.05.007"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2014.11.005"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2018.04.011"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2005.12.046"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1287\/trsc.2021.1045"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1287\/trsc.1120.0414"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1080\/01605682.2023.2253852"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2024.11.025"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.1287\/trsc.37.4.408.23271"},{"key":"B39","first-page":"269","volume-title":"Computer Scheduling of Public Transport: Urban Passenger Vehicle and Crew Scheduling","author":"Ryan DM","year":"1981"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.47.9.1290.9780"},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.1287\/trsc.32.3.232"},{"key":"B42","unstructured":"Tang Y, Agrawal S, Faenza Y (2020) Reinforcement learning for integer programming: Learning to cut. Daum\u00e9 H III, Singh A, eds.\n                      Proc. 37th Internat. Conf. Machine Learn.\n                      (PMLR, New York), 9367\u20139376."},{"key":"B43","doi-asserted-by":"publisher","DOI":"10.1016\/0377-2217(84)90207-8"},{"key":"B44","unstructured":"Vance PH, Atamturk A, Barnhart C, Gelman E, Johnson EL, Krishna A, Mahidhara D, Nemhauser GL, Rebello R (1997) A heuristic branch-and-price approach for the airline crew pairing problem. Technical report TLI\/LEC-97-06, Georgia Institute of Technology, Atlanta."},{"key":"B45","doi-asserted-by":"publisher","DOI":"10.1016\/j.tre.2017.03.005"},{"key":"B46","doi-asserted-by":"publisher","DOI":"10.3141\/2569-05"},{"key":"B47","doi-asserted-by":"publisher","DOI":"10.1287\/trsc.2018.0834"},{"key":"B48","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2018.02.013"},{"key":"B49","doi-asserted-by":"publisher","DOI":"10.1287\/inte.33.1.5.12720"}],"container-title":["Transportation Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubsonline.informs.org\/doi\/pdf\/10.1287\/trsc.2025.0105","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T08:20:59Z","timestamp":1773994859000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubsonline.informs.org\/doi\/10.1287\/trsc.2025.0105"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":49,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,3]]}},"alternative-id":["10.1287\/trsc.2025.0105"],"URL":"https:\/\/doi.org\/10.1287\/trsc.2025.0105","relation":{},"ISSN":["0041-1655","1526-5447"],"issn-type":[{"value":"0041-1655","type":"print"},{"value":"1526-5447","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}