Optimization of dynamic ticket pricing parameters

Abstract

This paper proposes a joint pricing model that combines the advantages of variable and dynamic ticket pricing models, where optimal dynamic prices are calculated for sporting events based on game-, time-, and inventory-related factors. These prices are based on a reference price and several different multipliers. Three different scenarios are investigated to reveal the most effective pricing model, together with corresponding simulation models. For the first time, a fuzzy logic model is used to predict the game multiplier, which reflects the characteristics of each individual game. The required demand information is predicted by an adaptive neuro-fuzzy inference system (ANFIS) model, and the price multiplier parameters are optimized to maximize the expected total revenue. Results based on real sporting data show that the new dynamic strategies were able to increase the expected revenue compared with a traditional static pricing strategy, indicating that all three joint pricing model scenarios could be utilized effectively to price sporting event tickets.