Learning competitive dynamic airline pricing under different customer models

There is a tendency to focus on the overly simplistic dynamic airline pricing games or to even ignore competition completely, because of the difficulty in solving game theoretic models. Recent changes in the industry mean that airlines can no longer ignore competitors in their model. This article adds more complex customer model aspects – that is, customer choice using a logit model, customer demand using a linear probabilistic demand model and market size using a binary random function – into an existing solvable airline pricing game; originally, this game only used a simple customer model. The newly formed games were solved using a reinforcement learning algorithm with mixed results.