Dynamic air ticket pricing using reinforcement learning method

Abstract

This paper studies a dynamic air ticket pricing problem in a strategic and myopic passengers’ co-existence market. The strategic or myopic passengers can be further divided into high-valuation and low-valuation groups according to how they evaluate their purchases. The strategic passengers have different strategic levels. When the airline sets a ticket price, every passenger makes his or her purchase decision according to his or her type and the strategic level, or might select “wait” or “leave (the market)”. The paper firstly proposes a dynamic pricing algorithm in which the utilities of both the airline and passengers are considered. The reinforcement learning (RL) is employed to deal with the progressive or dynamic decision-making framework, in which the dynamic pricing problem is formulated as a discrete finite Markov decision process (MDP) and the Q-learning is adopted to solve the problem. By using this method, the airline can adaptively decide the ticket price based on passengers’ strategic behaviors and the time-varying demand. The effects of the passenger type proportion and strategic level are analyzed. The computational results show the higher proportion of strategic passengers is, the smaller price increase the airline can adopt, and the higher proportion of high-valuation strategic passengers is, the larger price increase the airline can put to use under the same strategic level. If the proportion of low-valuation strategic passengers is higher, the price increase should be gentle and step by step when the price increase strategy is adopted. If the airline uses price-cut policy, the adjustment should be small. In addition, the high-valuation passenger mainly affects high-price periods and the low-valuation passenger mainly affects low-price periods. When the proportion of strategic passengers is fixed, the lower the passenger strategic level is, the larger the price slope is. These findings can provide some references for the airline to make more precise and flexible pricing decisions.

Distributed Dynamic Pricing Strategy Based on Deep Reinforcement Learning Approach in a Presale Mechanism

“…Q-learning algorithm converges Q π (s, a) through continuous iteration, and its stateaction pair updating method is shown in Formula (8), where a represents the learning rate, γ represents the decay coefficient of the reward, and a ∈ [0, 1]:…”

“…Accordingly, dynamic pricing has become the preferred option for most retailers that can routinely alter prices according to inventory and demand information, which is also an essential component of price strategy [6,7]. Dynamic pricing strategy applies to various industries, such as airline and energy [8,9], which has extended to online retail [10]. Ecommerce platforms have severe centralization, information islands, and trust issues as their scale grows, which has a negative impact on the supply chain's overall efficiency [11,12].…”

Relationship between Airline Ticket Price, Demand and Business Model: A Worldwide Analysis

“…A review of the literature on air transport shows that there have been many studies on ticket prices and the factors that have had an impact on ticket prices. Gao et al (2022) conducted a study on a dynamic pricing algorithm that considers both airlines and passengers. The result of the research shows that if the ratio of low-value strategic passengers is higher, the price increase should be smooth and gradual when the price increase strategy is adopted.…”