Transformer‐based choice model: A tool for assortment optimization evaluation

Assessing the efficacy of algorithms plays a pivotal role in advancing various fields, both in theory and practice. Unlike the predictive models, due to the intricate relationship between decisions and the underlying data‐generating processes, the evaluation of decision algorithms cannot directly rely on real data. Hence, a simulator becomes indispensable for appraising decision algorithm effectiveness. In this paper, we aim to leverage assortment decisions, a widely used application in revenue management, to illustrate the utilization of a machine learning‐based simulation. The process can be summarised as: we utilize the modified Transformer‐based choice model, acting as a simulator, to generate a synthetic dataset that mimics consumer purchasing behavior. After training the MNL, DeepFM, and DeepFM‐a models, all of which can swiftly provide assortment decisions in real‐time, we utilize the simulator to evaluate the revenue generated by each assortment prescribed by different choice models. This approach mitigates the challenge of validating decision models that alter real‐world observed data. To show the benefit of such a simulation approach, we have conducted various numerical studies. These studies aim to examine the impact of outside option attractiveness, data size, the number of features, and cardinality. Admittedly, due to the close alignment between the simulator and complex consumer purchase choice datasets, some numerical observations may be challenging to explain. Nevertheless, by employing the simulator, we are able to contrast the differences between the MNL and DeepFM/DeepFM‐a models, shedding light on their respective model misspecifications.