Reinforcement learning for content's customization: a first step of experimentation in Skyscanner

Abstract

PurposeThe 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.Design/methodology/approachThe 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 software.FindingsThe first results are about the comparison between the two approaches – A/B testing and multi-armed bandits – 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.Research limitations/implicationsThe 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.Practical implicationsThe 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.Originality/valueThe 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.

International air travel attitude and travel planning lead times across 45 countries in response to the COVID-19 pandemic

“…Researchers increasingly use Big Data from mobile applications, social networks and web tools to better monitor and understand the needs of tourists (Li & Law, 2020;Li, Xu, Tang, Wang, & Li, 2018). This study uses data from Skyscanner, a travel metasearch engine used monthly by >100 million people worldwide (Giachino, Bollani, Bonadonna, & Bertetti, 2021). Skyscanner allows users to define the search parameters (origin, destination, travel dates, number of travellers, etc.)…”

Intelligent Content Distribution System: A Machine Learning–Based Teaching Content Customization Method

“…However, existing methods of customizing and distributing teaching content still face many challenges in practical application. First, many methods fail to fully consider the configuration of teaching content combinations and its complex relationship with students' needs, resulting in distributed content not optimally meeting their needs [23][24][25]. Second, existing teaching content distribution methods are often complex and require a large amount of computing resources, which is not feasible in large-scale educational scenarios.…”

Guest editorial: New technologies for the tourism and hospitality industry

“…The twelfth article, co-authored by Chiara Giachino, Luigi Bollani, Alessandro Bonadonna and Marco Bertetti, is "Reinforcement learning for content's customization: a first step of experimentation in Skyscanner," which tests the potential benefits of applying reinforcement learning to optimize the content of a company's mobile application to best help travelers find their ideal flights. The authors found that simulation of reinforcement learning provides potential benefits for travelers (Giachino et al, 2021).…”