Reinforcement learning applied to airline revenue management

Bondoux, Nicolas; Nguyen, Anh Quan; Fiig, Thomas; Acuña-Agost, Rodrigo

doi:10.1057/s41272-020-00228-4

Cited by 30 publications

(19 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…He has to set a price that is forcing the competitor toward an unprofitable reaction and allows a sustainable high price level in the market. This necessity distinguishes the following experiments from other evaluations of RL on dynamic pricing, cf., e.g., Bondoux et al (2020).…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Dynamic pricing under competition using reinforcement learning

Kastius

Schlößer

2021

J Revenue Pricing Manag

View full text Add to dashboard Cite

Dynamic pricing is considered a possibility to gain an advantage over competitors in modern online markets. The past advancements in Reinforcement Learning (RL) provided more capable algorithms that can be used to solve pricing problems. In this paper, we study the performance of Deep Q-Networks (DQN) and Soft Actor Critic (SAC) in different market models. We consider tractable duopoly settings, where optimal solutions derived by dynamic programming techniques can be used for verification, as well as oligopoly settings, which are usually intractable due to the curse of dimensionality. We find that both algorithms provide reasonable results, while SAC performs better than DQN. Moreover, we show that under certain conditions, RL algorithms can be forced into collusion by their competitors without direct communication.

show abstract

Section: Methodsmentioning

confidence: 99%

“…In a recent publication, Bondoux et al provide an extensive study on the possible use of reinforcement learning for airline revenue management; see Bondoux et al (2020). They show that Deep Q-Networks provides a feasible algorithm for such systems.…”

Section: Related Workmentioning

confidence: 99%

Dynamic pricing under competition using reinforcement learning

Kastius

Schlößer

2021

J Revenue Pricing Manag

View full text Add to dashboard Cite

show abstract

“…Reinforcement learning is extensively applied in the dynamic pricing framework [6], [26], [43]- [47]. For example, the authors of [26] employ Q-learning for dynamic pricing and demand learning.…”

Section: Volume 4 2016mentioning

confidence: 99%

“…Dynamic pricing is defined as setting a time-varying price for a certain product or service [2], [3]. Recently, dynamic pricing is broadly applicable in various domains such as: hotel revenue management [4], airline industry [5], [6], mobile data services [7], electricity [8], [9] and [10], and e-services [11]. However, there is a fundamental challenge when applying dynamic pricing, which is how to set prices optimally in order to maximize revenue returns.…”

Section: Introductionmentioning

confidence: 99%

Multi-Step Look-Ahead Optimization Methods for Dynamic Pricing With Demand Learning

2021

View full text Add to dashboard Cite

Dynamic pricing is a beneficial strategy for firms seeking to achieve high revenues. It has been widely applied to various domains such as the airline industry, the hotel industry, and e-services. Dynamic pricing is basically the problem of setting time-varying prices for a certain product or service for the purpose of optimizing revenue. However, a major challenge encountered when applying dynamic pricing is the lack of knowledge of the demand-price curve. The demand-price curve defines the customer's response towards changing the price. In this work, we address the dynamic pricing problem in case of unknown demandprice relation. This work introduces a less myopic pricing approach based on looking ahead for one or several future steps in our quest to optimize revenue. Specifically, the proposed formulation maximizes the summation of the immediate revenue and the expected future revenues of one or multiple look-ahead steps.A key benefit of the proposed approach is that it automatically strikes a balance between the conflicting goals of revenue maximization and demand learning, by producing less myopic and profitable prices. We provide a formulation for the presented look-ahead pricing approach, and we implement two variants of it: one-step and two-step look-ahead methods. Experiments are conducted on synthetic and real datasets to compare the proposed pricing methods to other pricing strategies in literature. The experimental results indicate that the proposed look-ahead methods outperform their counterparts in terms of the achieved revenue gain.

show abstract

“…Moreover, reinforcement learning is useful for the management of the airlines revenue system, and it can directly learn from the interaction with customers (Bondoux et al, 2020) or facilitate the management activity in setting the prices of airline tickets in a specific time horizon for booking (Kulkarny et al, 2011). Another well-known example of reinforcement learning implementation is the engine behind the system used by Netflix to provide clients with personalized recommendations to movies and TV series that they may like to watch next and to select which creative to display on each title to make it more appealing to them (Medium, 2019).…”

Section: Reinforcement Learning For Content's Customization 1417mentioning

confidence: 99%

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

Giachino

Bollani

Bonadonna

et al. 2021

IMDS

View full text Add to dashboard Cite

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.

show abstract

Reinforcement learning applied to airline revenue management

Cited by 30 publications

References 14 publications

Dynamic pricing under competition using reinforcement learning

Dynamic pricing under competition using reinforcement learning

Multi-Step Look-Ahead Optimization Methods for Dynamic Pricing With Demand Learning

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

Contact Info

Product

Resources

About