{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T22:11:01Z","timestamp":1761948661598,"version":"3.41.2"},"reference-count":58,"publisher":"Emerald","issue":"6","license":[{"start":{"date-parts":[[2021,1,15]],"date-time":"2021-01-15T00:00:00Z","timestamp":1610668800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.emerald.com\/insight\/site-policies"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IMDS"],"published-print":{"date-parts":[[2021,6,7]]},"abstract":"Purpose<\/jats:title>The aim of the paper is to test and demonstrate the potential benefits in applying reinforcement learning instead of traditional methods to optimize the content of a company's mobile application to best help travellers finding their ideal flights. To this end, two approaches were considered and compared via simulation: standard randomized experiments or A\/B testing and multi-armed bandits.<\/jats:p><\/jats:sec>Design\/methodology\/approach<\/jats:title>The simulation of the two approaches to optimize the content of its mobile application and, consequently, increase flights conversions is illustrated as applied by Skyscanner, using R<\/jats:italic> software.<\/jats:p><\/jats:sec>Findings<\/jats:title>The first results are about the comparison between the two approaches \u2013 A\/B testing and multi-armed bandits \u2013 to identify the best one to achieve better results for the company. The second one is to gain experiences and suggestion in the application of the two approaches useful for other industries\/companies.<\/jats:p><\/jats:sec>Research limitations\/implications<\/jats:title>The case study demonstrated, via simulation, the potential benefits to apply the reinforcement learning in a company. Finally, the multi-armed bandit was implemented in the company, but the period of the available data was limited, and due to its strategic relevance, the company cannot show all the findings.<\/jats:p><\/jats:sec>Practical implications<\/jats:title>The right algorithm can change according to the situation and industry but would bring great benefits to the company's ability to surface content that is more relevant to users and help improving the experience for travellers. The study shows how to manage complexity and data to achieve good results.<\/jats:p><\/jats:sec>Originality\/value<\/jats:title>The paper describes the approach used by an European leading company operating in the travel sector in understanding how to adapt reinforcement learning to its strategic goals. It presents a real case study and the simulation of the application of A\/B testing and multi-armed bandit in Skyscanner; moreover, it highlights practical suggestion useful to other companies.<\/jats:p><\/jats:sec>","DOI":"10.1108\/imds-12-2019-0722","type":"journal-article","created":{"date-parts":[[2021,1,15]],"date-time":"2021-01-15T22:13:12Z","timestamp":1610748792000},"page":"1417-1434","source":"Crossref","is-referenced-by-count":5,"title":["Reinforcement learning for content's customization: a first step of experimentation in Skyscanner"],"prefix":"10.1108","volume":"121","author":[{"given":"Chiara","family":"Giachino","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luigi","family":"Bollani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alessandro","family":"Bonadonna","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marco","family":"Bertetti","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"140","published-online":{"date-parts":[[2021,1,15]]},"reference":[{"key":"key2021060810250793600_ref001","unstructured":"Amstrong, S., Esber, D., Heller, J. and Timelin, B. (2020), \u201cModern marketing: what it is, what it isn't and how do it\u201d, McKinsey and Company Report, available at: https:\/\/www.mckinsey.com\/business-functions\/marketing-and-sales\/our-insights\/modern-marketing-what-it-is-what-it-isnt-and-how-to-do-it (accessed March 2020)."},{"first-page":"874","article-title":"Emotionally motivated reinforcement learning based controller","year":"2004","key":"key2021060810250793600_ref002"},{"issue":"2","key":"key2021060810250793600_ref003","doi-asserted-by":"crossref","first-page":"500","DOI":"10.1016\/j.dss.2004.08.015","article-title":"Simulating sellers in online exchanges","volume":"41","year":"2006","journal-title":"Decision Support Systems"},{"issue":"5","key":"key2021060810250793600_ref004","doi-asserted-by":"publisher","first-page":"332","DOI":"10.1057\/s41272-020-00228-4","article-title":"Reinforcement learning applied to airline revenue management","volume":"19","year":"2020","journal-title":"Journal of Revenue and Pricing Management"},{"year":"2020","key":"key2021060810250793600_ref005","article-title":"Learning to plan in high dimensions via neural exploration-exploitation trees"},{"article-title":"Marketing malpractice. Make sure all your products are profitable","volume-title":"Havard Business Review","year":"2005","key":"key2021060810250793600_ref006"},{"issue":"2","key":"key2021060810250793600_ref007","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1016\/j.tele.2014.08.005","article-title":"The use of social media in travel information search","volume":"32","year":"2015","journal-title":"Telematics and Informatics"},{"issue":"9","key":"key2021060810250793600_ref008","doi-asserted-by":"crossref","first-page":"902","DOI":"10.1080\/0144929X.2015.1039060","article-title":"Adoption of travel information in user-generated content on social media: the moderating effect of social presence","volume":"34","year":"2015","journal-title":"Behaviour and Information Technology"},{"key":"key2021060810250793600_ref009","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1016\/j.techfore.2015.03.004","article-title":"The influence of tourism website on tourists' behavior to determine destination selection: a case study of creative economy in Korea","volume":"96","year":"2015","journal-title":"Technological Forecasting and Social Change"},{"key":"key2021060810250793600_ref010","unstructured":"DeepMind (2019), \u201cOpen sources deep mind lab\u201d, available at: https:\/\/deepmind.com\/blog\/open-sourcing-deepmind-lab\/ (accessed July 2019)."},{"issue":"2","key":"key2021060810250793600_ref011","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1016\/j.aci.2018.02.002","article-title":"Predicting rank for scientific research papers using supervised learning","volume":"15","year":"2019","journal-title":"Applied Computing and Informatics"},{"issue":"3","key":"key2021060810250793600_ref012","doi-asserted-by":"crossref","first-page":"523","DOI":"10.3758\/s13415-015-0347-6","article-title":"Model-based learning protects against forming habits","volume":"15","year":"2015","journal-title":"Cognitive, Affective, and Behavioral Neuroscience"},{"year":"2017","key":"key2021060810250793600_ref013","article-title":"When user experience designers partner with data scientists"},{"key":"key2021060810250793600_ref014","unstructured":"Hu, J. (2016), \u201cReinforcement learning explained\u201d, available at: https:\/\/www.oreilly.com\/ideas\/reinforcement-learning-explained (accessed July 2019)."},{"first-page":"1","article-title":"Second-best beam-alignment via bayesian multi-armed bandits","year":"2019","key":"key2021060810250793600_ref015"},{"issue":"2009","key":"key2021060810250793600_ref043","first-page":"39","article-title":"Online experimentation at Microsoft","volume":"11","year":"2009","journal-title":"Data Mining Case Studies"},{"key":"key2021060810250793600_ref016","first-page":"1","article-title":"Algorithms for the multi-armed bandit problem","volume":"1","year":"2000","journal-title":"Journal of Machine Learning Research"},{"issue":"3","key":"key2021060810250793600_ref017","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1007\/s11768-011-0161-9","article-title":"Semi-Markov adaptive critic heuristics with application to airline revenue management","volume":"9","year":"2011","journal-title":"Journal of Control Theory and Applications"},{"issue":"10","key":"key2021060810250793600_ref018","first-page":"1854","article-title":"A short introduction to learning to rank","volume":"94","year":"2011","journal-title":"IEICE Transactions on Information and Systems"},{"first-page":"661","article-title":"A contextual-bandit approach to personalized news article recommendation","year":"2010","key":"key2021060810250793600_ref019"},{"issue":"3","key":"key2021060810250793600_ref020","first-page":"225","article-title":"Learning to rank for information retrieval","volume":"3","year":"2009","journal-title":"Foundations and Trends\u00ae in Information Retrieval"},{"first-page":"31","article-title":"Explore, exploit, and explain: personalizing explainable recommendations with bandits","year":"2018","key":"key2021060810250793600_ref021"},{"key":"key2021060810250793600_ref022","unstructured":"Medium (2019), \u201cArtwork personalization at Netflix\u201d, available at: https:\/\/medium.com\/netflix-techblog\/artwork-personalization-c589f074ad76 (accessed July 2019)."},{"issue":"1","key":"key2021060810250793600_ref023","first-page":"80","article-title":"Can machine learning techniques predict customer dissatisfaction? A feasibility study for the automotive industry","volume":"6","year":"2017","journal-title":"Artificial Intelligence Research"},{"issue":"2","key":"key2021060810250793600_ref024","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1287\/mksc.2018.1129","article-title":"Dynamic online pricing with incomplete information using multiarmed bandit experiments","volume":"38","year":"2019","journal-title":"Marketing Science"},{"issue":"7","key":"key2021060810250793600_ref025","first-page":"1136","article-title":"Reinforcement learning on a futures market simulator","volume":"14","year":"2008","journal-title":"Journal of Universal Computer Science"},{"issue":"7","key":"key2021060810250793600_ref026","doi-asserted-by":"publisher","first-page":"483","DOI":"10.14569\/ijacsa.2019.0100766","article-title":"Cas-GANs: an approach of dialogue policy learning based on GAN and RL techniques","volume":"10","year":"2019","journal-title":"International Journal of Advanced Computer Science and Applications"},{"issue":"21","key":"key2021060810250793600_ref027","doi-asserted-by":"crossref","first-page":"6013","DOI":"10.3390\/su11216013","article-title":"A hybrid method with TOPSIS and machine learning techniques for sustainable development of green hotels considering online reviews","volume":"11","year":"2019","journal-title":"Sustainability"},{"key":"key2021060810250793600_ref028","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1016\/j.dss.2013.05.003","article-title":"A machine learning-based usability evaluation method for eLearning systems","volume":"56","year":"2013","journal-title":"Decision Support Systems"},{"first-page":"784","article-title":"Learning diverse rankings with multi-armed bandits","year":"2008","key":"key2021060810250793600_ref029"},{"issue":"3","key":"key2021060810250793600_ref030","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1023\/A:1015008417172","article-title":"Reinforcement learning agents","volume":"17","year":"2002","journal-title":"Artificial Intelligence Review"},{"issue":"5","key":"key2021060810250793600_ref031","doi-asserted-by":"crossref","first-page":"527","DOI":"10.1090\/S0002-9904-1952-09620-8","article-title":"Some aspects of the sequential design of experiments","volume":"58","year":"1952","journal-title":"Bulletin of the American Mathematical Society"},{"article-title":"Learning and decisions in contextual multi-armed bandit tasks","volume-title":"CogSci","year":"2015","key":"key2021060810250793600_ref032"},{"issue":"7676","key":"key2021060810250793600_ref033","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the game of go without human knowledge","volume":"550","year":"2017","journal-title":"Nature"},{"first-page":"1031","article-title":"Model-based reinforcement learning with nearly tight exploration complexity bounds","year":"2010","key":"key2021060810250793600_ref034"},{"year":"2015","key":"key2021060810250793600_ref035","article-title":"Multi\u2013armed bandit for pricing"},{"volume-title":"What Customers Want","year":"2005","key":"key2021060810250793600_ref036"},{"volume-title":"Jobs to Be Done: Theory to Practice","year":"2016","key":"key2021060810250793600_ref037"},{"issue":"1","key":"key2021060810250793600_ref038","first-page":"91","article-title":"Turn customer input into innovation","volume":"80","year":"2002","journal-title":"Harvard Business Review"},{"year":"2018","key":"key2021060810250793600_ref044","article-title":"Contextual: evaluating contextual multi-armed bandit problems in R"},{"first-page":"3844","article-title":"Airdialogue: an environment for goal-oriented dialogue research","year":"2018","key":"key2021060810250793600_ref039"},{"volume-title":"Bandit Algorithms for Website Optimization","year":"2012","key":"key2021060810250793600_ref040"},{"first-page":"445","article-title":"Enhancing collaborative filtering music recommendation by balancing exploration and exploitation","year":"2014","key":"key2021060810250793600_ref041"},{"first-page":"2227","article-title":"From infrastructure to culture: A\/B testing challenges in large scale social networks","year":"2015","key":"key2021060810250793600_ref042"},{"issue":"1","key":"key2021060810250793600_fur1","doi-asserted-by":"publisher","first-page":"3482","DOI":"10.35940\/ijitee.A4936.119119","article-title":"Credit risk assessment using machine learning techniques","volume":"9","year":"2019","journal-title":"International Journal of Innovative Technology and Exploring Engineering"},{"issue":"2","key":"key2021060810250793600_fur2","first-page":"94","article-title":"Customer relationship management and big data enabled: personalization and customization of services","volume":"15","year":"2018","journal-title":"Applied Computing and Informatics"},{"first-page":"728","article-title":"Semi-supervised learning based aesthetic classifier for short animations embedded in Web pages","year":"2013","key":"key2021060810250793600_fur3"},{"issue":"30","key":"key2021060810250793600_fur4","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1007\/s12525-019-00351-0","article-title":"Supporting customer-oriented marketing with artificial intelligence: automatically quantifying customer needs from social media","year":"2019","journal-title":"Electronic Markets"},{"key":"key2021060810250793600_fur5","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1016\/j.jocm.2018.02.002","article-title":"Airline itinerary choice modeling using machine learning","volume":"31","year":"2019","journal-title":"Journal of Choice Modelling"},{"key":"key2021060810250793600_fur6","doi-asserted-by":"publisher","first-page":"102023","DOI":"10.1016\/j.simpat.2019.102023","article-title":"A new machine learning method for identifying Alzheimer's disease","volume":"99","year":"2020","journal-title":"Simulation Modelling Practice and Theory"},{"issue":"19","key":"key2021060810250793600_fur7","doi-asserted-by":"publisher","first-page":"5254","DOI":"10.3390\/su11195254","article-title":"Predicting the helpfulness of online restaurant reviews using different machine learning algorithms: a case study of yelp","volume":"11","year":"2019","journal-title":"Sustainability"},{"issue":"1","key":"key2021060810250793600_fur8","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1109\/TCSS.2019.2891126","article-title":"Is my interface beautiful?\u2014a computational model-based approach","volume":"6","year":"2019","journal-title":"IEEE Transactions on Computational Social Systems"},{"key":"key2021060810250793600_fur9","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1007\/978-3-030-32520-6_10","article-title":"Machine learning analysis of mortgage credit risk","volume":"1069","year":"2020","journal-title":"Advances in Intelligent Systems and Computing"},{"issue":"8","key":"key2021060810250793600_fur10","first-page":"1681","article-title":"Managing regional consumer market based on the improved approach to evaluating customer needs for food commodities","volume":"11","year":"2016","journal-title":"Journal of Applied Economic Sciences"},{"issue":"1","key":"key2021060810250793600_fur11","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1300\/J179v06n01_02","article-title":"Investigating antecedents of behavioral intentions in mobile commerce","volume":"6","year":"2008","journal-title":"Journal of Internet Commerce"},{"issue":"1","key":"key2021060810250793600_fur12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1287\/mksc.2018.1123","article-title":"Identifying customer needs from user-generated content","volume":"38","year":"2019","journal-title":"Marketing Science"},{"key":"key2021060810250793600_fur13","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrad.2019.108755","article-title":"Machine learning-based multiparametric MRI radiomics for predicting the aggressiveness of papillary thyroid carcinoma","volume":"122","year":"2020","journal-title":"European Journal of Radiology"},{"issue":"10","key":"key2021060810250793600_fur14","doi-asserted-by":"publisher","DOI":"10.3390\/su10103564","article-title":"An approach to discovering product\/service improvement priorities: using dynamic importance-performance analysis","volume":"10","year":"2018","journal-title":"Sustainability"}],"container-title":["Industrial Management & Data Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/IMDS-12-2019-0722\/full\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/IMDS-12-2019-0722\/full\/html","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T21:54:22Z","timestamp":1753394062000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.emerald.com\/imds\/article\/121\/6\/1417-1434\/431214"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,15]]},"references-count":58,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2021,1,15]]},"published-print":{"date-parts":[[2021,6,7]]}},"alternative-id":["10.1108\/IMDS-12-2019-0722"],"URL":"https:\/\/doi.org\/10.1108\/imds-12-2019-0722","relation":{},"ISSN":["0263-5577"],"issn-type":[{"type":"print","value":"0263-5577"}],"subject":[],"published":{"date-parts":[[2021,1,15]]}}}