Product2Vec: Leveraging representation learning to model consumer product choice in large assortments

83 Pages Posted: 7 Feb 2020 Last revised: 3 Jul 2022

See all articles by Fanglin Chen

Fanglin Chen

New York University (NYU) - New York University (NYU), Leonard N. Stern School of Business, Department of Marketing, Students

Xiao Liu

New York University (NYU) - Leonard N. Stern School of Business

Davide Proserpio

Marshall School of Business, University of Southern California

Isamar Troncoso

Harvard Business School

Date Written: July 1, 2022

Abstract

We propose a method, Product2Vec, based on representation learning, that can automatically learn latent product attributes that drive consumer choices, to study product-level competition when the number of products is large. We demonstrate Product2Vec’s interpretability and capability for scalable causal inference. For interpretability, first, we theoretically demonstrate that there exists a direct link between product vectors and product attributes by deriving a formal proof. Second, we use product embedding to create two metrics, complementarity and exchangeability, that allow us to distinguish between products that are complements and substitutes, respectively. For causal inference, we combine product vectors with choice models and show that we can achieve better accuracy—both in terms of model fit and unbiased price coefficients—when compared to a model based solely on observable attributes, and obtain results similar to those obtained with a more complex model that includes a fixed effect for every product.

Keywords: machine learning, product competition, representation learning, choice models

Suggested Citation

Chen, Fanglin and Liu, Xiao and Proserpio, Davide and Troncoso, Isamar, Product2Vec: Leveraging representation learning to model consumer product choice in large assortments (July 1, 2022). NYU Stern School of Business, Available at SSRN: https://ssrn.com/abstract=3519358 or http://dx.doi.org/10.2139/ssrn.3519358

Fanglin Chen (Contact Author)

New York University (NYU) - New York University (NYU), Leonard N. Stern School of Business, Department of Marketing, Students ( email )

Henry Kaufman Ctr
44 W 4 St.
New York, NY
United States

Xiao Liu

New York University (NYU) - Leonard N. Stern School of Business ( email )

Suite 9-160
New York, NY
United States

Davide Proserpio

Marshall School of Business, University of Southern California ( email )

701 Exposition Blvd
Los Angeles, CA Los Angeles 90089
United States

HOME PAGE: http://dadepro.github.io/

Isamar Troncoso

Harvard Business School ( email )

15 Harvard Way
Boston, MA 02163
United States

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

Paper statistics

Downloads
1,966
Abstract Views
5,933
rank
12,262
PlumX Metrics