Combinatorial Inference on the Optimal Assortment in Multinomial Logit Models

TL;DR

This paper introduces a new statistical inference framework for testing properties of the optimal product assortment in multinomial logit models, focusing on uncertainty quantification rather than full estimation.

Contribution

It develops a novel hypothesis testing method for properties of the optimal assortment, utilizing asymptotic normality and bootstrap techniques within the MNL model.

Findings

The proposed method accurately detects property violations in simulated data.

The asymptotic normality of the marginal revenue gap estimator is established.

Numerical experiments demonstrate the effectiveness of the testing procedure.

Abstract

Assortment optimization has received active explorations in the past few decades due to its practical importance. Despite the extensive literature dealing with optimization algorithms and latent score estimation, uncertainty quantification for the optimal assortment still needs to be explored and is of great practical significance. Instead of estimating and recovering the complete optimal offer set, decision-makers may only be interested in testing whether a given property holds true for the optimal assortment, such as whether they should include several products of interest in the optimal set, or how many categories of products the optimal set should include. This paper proposes a novel inferential framework for testing such properties. We consider the widely adopted multinomial logit (MNL) model, where we assume that each customer will purchase an item within the offered products with a probability proportional to the underlying preference score associated with the product. We reduce inferring a general optimal assortment property to quantifying the uncertainty associated with the sign change point detection of the marginal revenue gaps. We show the asymptotic normality of the marginal revenue gap estimator, and construct a maximum statistic via the gap estimators to detect the sign change point. By approximating the distribution of the maximum statistic with multiplier bootstrap techniques, we propose a valid testing procedure. We also conduct numerical experiments to assess the performance of our method.