{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T07:50:39Z","timestamp":1765871439811,"version":"3.48.0"},"reference-count":25,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T00:00:00Z","timestamp":1763337600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T00:00:00Z","timestamp":1763337600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"the National Key R&D Program of China","award":["2022YFA1003900"],"award-info":[{"award-number":["2022YFA1003900"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["CCF Trans. HPC"],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1007\/s42514-025-00251-0","type":"journal-article","created":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T11:06:03Z","timestamp":1763377563000},"page":"632-642","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Reinforcement learning for airline multi-class continuous dynamic pricing"],"prefix":"10.1007","volume":"7","author":[{"given":"Zhicheng","family":"Yao","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8441-7334","authenticated-orcid":false,"given":"Wenguo","family":"Yang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,17]]},"reference":[{"key":"251_CR1","unstructured":"Belobaba, P.: Air travel demand and airline seat inventory management. Ph.D. thesis, Massachusetts Institute of Technology (1987)"},{"key":"251_CR2","unstructured":"Belobaba, P.P.: Optimal vs. heuristic methods for nested seat allocation. In: Presentation at ORSA\/TIMS Joint National Meeting. vol.\u00a01 (1992)"},{"issue":"6","key":"251_CR3","doi-asserted-by":"publisher","first-page":"1537","DOI":"10.1287\/opre.1120.1103","volume":"60","author":"O Besbes","year":"2012","unstructured":"Besbes, O., Zeevi, A.: Blind network revenue management. Oper. Res. 60(6), 1537\u20131550 (2012)","journal-title":"Oper. Res."},{"key":"251_CR4","doi-asserted-by":"publisher","first-page":"332","DOI":"10.1057\/s41272-020-00228-4","volume":"19","author":"N Bondoux","year":"2020","unstructured":"Bondoux, N., Nguyen, A.Q., Fiig, T., Acuna-Agost, R.: Reinforcement learning applied to airline revenue management. J. Rev. Pric. Manage. 19, 332\u2013348 (2020). https:\/\/doi.org\/10.1057\/s41272-020-00228-4","journal-title":"J. Rev. Pric. Manage."},{"issue":"4","key":"251_CR5","doi-asserted-by":"publisher","first-page":"965","DOI":"10.1287\/opre.1120.1057","volume":"60","author":"J Broder","year":"2012","unstructured":"Broder, J., Rusmevichientong, P.: Dynamic pricing under a general parametric choice model. Oper. Res. 60(4), 965\u2013980 (2012)","journal-title":"Oper. Res."},{"issue":"3","key":"251_CR6","doi-asserted-by":"publisher","first-page":"770","DOI":"10.1287\/mnsc.2013.1788","volume":"60","author":"AV Den Boer","year":"2014","unstructured":"Den Boer, A.V., Zwart, B.: Simultaneously learning and optimizing using controlled variance pricing. Manage. Sci. 60(3), 770\u2013783 (2014)","journal-title":"Manage. Sci."},{"issue":"8","key":"251_CR7","doi-asserted-by":"publisher","first-page":"999","DOI":"10.1287\/mnsc.40.8.999","volume":"40","author":"G Gallego","year":"1994","unstructured":"Gallego, G., Van Ryzin, G.: Optimal dynamic pricing of inventories with stochastic demand over finite horizons. Manage. Sci. 40(8), 999\u20131020 (1994)","journal-title":"Manage. Sci."},{"issue":"1","key":"251_CR8","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1287\/opre.45.1.24","volume":"45","author":"G Gallego","year":"1997","unstructured":"Gallego, G., Van Ryzin, G.: A multiproduct dynamic pricing problem and its applications to network yield management. Oper. Res. 45(1), 24\u201341 (1997)","journal-title":"Oper. Res."},{"key":"251_CR9","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/B:MACH.0000019802.64038.6c","volume":"55","author":"A Gosavi","year":"2004","unstructured":"Gosavi, A.: A reinforcement learning algorithm based on policy iteration for average reward: empirical results with yield management and convergence analysis. Mach. Learn. 55, 5\u201329 (2004). https:\/\/doi.org\/10.1023\/B:MACH.0000019802.64038.6c","journal-title":"Mach. Learn."},{"key":"251_CR10","doi-asserted-by":"publisher","first-page":"729","DOI":"10.1023\/A:1015583703449","volume":"34","author":"A Gosavi","year":"2002","unstructured":"Gosavi, A., Bandla, N., Das, T.K.: A reinforcement learning approach to a single leg airline revenue management problem with multiple fare classes and overbooking. IIE Trans. 34, 729\u2013742 (2002). https:\/\/doi.org\/10.1023\/A:1015583703449","journal-title":"IIE Trans."},{"key":"251_CR11","unstructured":"Haarnoja, T., Zhou, A., Hartikainen, K., Tucker, G., Ha, S., Tan, J., Kumar, V., Zhu, H., Gupta, A., Abbeel, P., et\u00a0al.: Soft actor-critic algorithms and applications (2018) arXiv:1812.05905"},{"key":"251_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.108073","volume":"133","author":"S Jo","year":"2024","unstructured":"Jo, S., Lee, G.M., Moon, I.: Airline dynamic pricing with patient customers using deep exploration-based reinforcement learning. Eng. Appl. Artif. Intell. 133, 108073 (2024)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"251_CR13","doi-asserted-by":"publisher","first-page":"2719","DOI":"10.1111\/poms.13075","volume":"28","author":"J Ke","year":"2019","unstructured":"Ke, J., Zhang, D., Zheng, H.: An approximate dynamic programming approach to dynamic pricing for network revenue management. Prod. Oper. Manag. 28, 2719\u20132737 (2019)","journal-title":"Prod. Oper. Manag."},{"issue":"5","key":"251_CR14","doi-asserted-by":"publisher","first-page":"1142","DOI":"10.1287\/opre.2014.1294","volume":"62","author":"NB Keskin","year":"2014","unstructured":"Keskin, N.B., Zeevi, A.: Dynamic pricing with an unknown demand model: asymptotically optimal semi-myopic policies. Oper. Res. 62(5), 1142\u20131167 (2014)","journal-title":"Oper. Res."},{"issue":"2","key":"251_CR15","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1287\/trsc.33.2.136","volume":"33","author":"CJ Lautenbacher","year":"1999","unstructured":"Lautenbacher, C.J., Stidham, S.: The underlying Markov decision process in the single-leg airline yield-management problem. Transp. Sci. 33(2), 136\u2013146 (1999)","journal-title":"Transp. Sci."},{"key":"251_CR16","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1016\/j.engappai.2019.04.008","volume":"82","author":"RJ Lawhead","year":"2019","unstructured":"Lawhead, R.J., Gosavi, A.: A bounded actor-critic reinforcement learning algorithm applied to airline revenue management. Eng. Appl. Artif. Intell. 82, 252\u2013262 (2019). https:\/\/doi.org\/10.1016\/j.engappai.2019.04.008. (https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0952197619300934)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"251_CR17","unstructured":"Liotta, N.J.: Airline revenue management for continuous pricing: class-based and classless methods. Ph.D. thesis, Massachusetts Institute of Technology (2019)"},{"key":"251_CR18","unstructured":"Littlewood, K.: Forecasting and control of passenger bookings. The Airline Group of the International Federation of Operational Research Societies 12, 95\u2013117 (1972). https:\/\/cir.nii.ac.jp\/crid\/1572543026074888192"},{"issue":"1","key":"251_CR19","first-page":"14","volume":"23","author":"Y Long","year":"2024","unstructured":"Long, Y., Belobaba, P.: Airline revenue management with segmented continuous pricing: methods and competitive effects. J. Rev. Pric. Manage. 23(1), 14\u201327 (2024)","journal-title":"J. Rev. Pric. Manage."},{"key":"251_CR20","unstructured":"Papen, A.: Competitive impacts of continuous pricing mechanisms in airline revenue management (2020)"},{"key":"251_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121252","volume":"237","author":"W Qiao","year":"2024","unstructured":"Qiao, W., Huang, M., Gao, Z., Wang, X.: Distributed dynamic pricing of multiple perishable products using multi-agent reinforcement learning. Expert Syst. Appl. 237, 121252 (2024). https:\/\/doi.org\/10.1016\/j.eswa.2023.121252","journal-title":"Expert Syst. Appl."},{"key":"251_CR22","doi-asserted-by":"publisher","first-page":"669","DOI":"10.1057\/s41272-021-00350-x","volume":"20","author":"B Szyma\u0144ski","year":"2021","unstructured":"Szyma\u0144ski, B., Belobaba, P.P., Papen, A.: Continuous pricing algorithms for airline RM: revenue gains and competitive impacts. J. Rev. Pric. Manage. 20, 669\u2013688 (2021). https:\/\/doi.org\/10.1057\/s41272-021-00350-x","journal-title":"J. Rev. Pric. Manage."},{"issue":"1","key":"251_CR23","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1111\/poms.13525","volume":"31","author":"C Yang","year":"2022","unstructured":"Yang, C., Feng, Y., Whinston, A.: Dynamic pricing and information disclosure for fresh produce: an artificial intelligence approach. Prod. Oper. Manag. 31(1), 155\u2013171 (2022). https:\/\/doi.org\/10.1111\/poms.13525","journal-title":"Prod. Oper. Manag."},{"issue":"1","key":"251_CR24","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1287\/ijoc.1110.0488","volume":"25","author":"D Zhang","year":"2013","unstructured":"Zhang, D., Lu, Z.: Assessing the value of dynamic pricing in network revenue management. INFORMS J. Comput. 25(1), 102\u2013115 (2013)","journal-title":"INFORMS J. Comput."},{"key":"251_CR25","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2024.110302","volume":"193","author":"X Zhu","year":"2024","unstructured":"Zhu, X., Jian, L., Chen, X., Zhao, Q.: Reinforcement learning for multi-flight dynamic pricing. Comput. Ind. Eng. 193, 110302 (2024)","journal-title":"Comput. Ind. Eng."}],"container-title":["CCF Transactions on High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42514-025-00251-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42514-025-00251-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42514-025-00251-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T07:47:23Z","timestamp":1765871243000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42514-025-00251-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,17]]},"references-count":25,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["251"],"URL":"https:\/\/doi.org\/10.1007\/s42514-025-00251-0","relation":{},"ISSN":["2524-4922","2524-4930"],"issn-type":[{"type":"print","value":"2524-4922"},{"type":"electronic","value":"2524-4930"}],"subject":[],"published":{"date-parts":[[2025,11,17]]},"assertion":[{"value":"29 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 November 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no conflict of interest to declare that are relevant to the content of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}