The Click-Based MNL Model: A Novel Framework for Modeling Click Data in Assortment Optimization

74 Pages Posted: 17 Mar 2019 Last revised: 1 Feb 2021

See all articles by Ali Aouad

Ali Aouad

London Business School

Jacob Feldman

Washington University in St. Louis - John M. Olin Business School

Danny Segev

Tel Aviv University - School of Mathematical Sciences

Dennis Zhang

Washington University in St. Louis - John M. Olin Business School

Date Written: February 23, 2019

Abstract

We introduce the click-based MNL choice model, a novel framework for capturing customer purchasing decisions in e-commerce settings. We augment the classical Multinomial Logit choice model with the assumption that customers only consider the items they have clicked on before they proceed to compare their random utilities. We propose a simple estimation framework that leverages clickstream data and machine learning classification algorithms. We study the resulting assortment optimization problem, where the objective is to select a subset of products, made available for purchase, to maximize the expected revenue. Our main algorithmic contribution comes in the form of a polynomial-time approximation scheme (PTAS) for this problem, showing that the optimal expected revenue can be efficiently approached within any degree of accuracy. In the course of establishing this result, we develop novel technical ideas, including enumeration schemes and stochastic inequalities, which may be of broader interest. Using data acquired in collaboration with Alibaba, we fit click-based MNL and Mixed MNL models to historical sales and click data in a setting where the online platform must present customized six-product displays to users. We show that our approach significantly outperforms the Mixed MNL models in terms of out-of-sample predictive accuracy, and the computational cost of its estimation process is smaller by an order of magnitude.

Keywords: Choice Models, Retailing Platforms, Assortment Optimization, Approximation Schemes, E-Commerce

Suggested Citation

Aouad, Ali and Feldman, Jacob and Segev, Danny and Zhang, Dennis, The Click-Based MNL Model: A Novel Framework for Modeling Click Data in Assortment Optimization (February 23, 2019). Available at SSRN: https://ssrn.com/abstract=3340620 or http://dx.doi.org/10.2139/ssrn.3340620

Ali Aouad

London Business School ( email )

Sussex Place
Regent's Park
London, London NW1 4SA
United Kingdom

Jacob Feldman

Washington University in St. Louis - John M. Olin Business School ( email )

One Brookings Drive
Campus Box 1133
St. Louis, MO 63130-4899
United States

Danny Segev (Contact Author)

Tel Aviv University - School of Mathematical Sciences ( email )

Tel Aviv 69978
Israel

Dennis Zhang

Washington University in St. Louis - John M. Olin Business School ( email )

One Brookings Drive
Campus Box 1133
St. Louis, MO 63130-4899
United States

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
519
Abstract Views
2,900
rank
67,740
PlumX Metrics