No Data? No Problem! A Search-Based Recommendation System With Cold Starts

44 Pages Posted: 30 Nov 2020

See all articles by Pedro Gardete

Pedro Gardete

Nova School of Business and Economics

Carlos Daniel Santos

New University of Lisbon - Nova School of Business and Economics

Date Written: October 5, 2020

Abstract

Recommendation systems are essential ingredients in producing matches between products and buyers. Despite their ubiquity, they face two important challenges. First, they are data-intensive, a feature that precludes sophisticated recommendations by some types of sellers, including those selling durable goods. Second, they often focus on estimating fixed evaluations of products by consumers while ignoring state-dependent behaviors identified in the Marketing literature.

We propose a recommendation system based on consumer browsing behaviors, which bypasses the “cold start” problem described above, and takes into account the fact that consumers act as “moving targets,” behaving differently depending on the recommendations suggested to them along their search journey. First, we recover the consumers' search policy function via machine learning methods. Second, we include that policy into the recommendation system's dynamic problem via a Bellman equation framework.

When compared with the seller's own recommendations, our system produces a profit increase of 33%. Our counterfactual analyses indicate that browsing history along with past recommendations feature strong complementary effects in value creation. Moreover, managing customer churn effectively is a big part of value creation, whereas recommending alternatives in a forward-looking way produces moderate effects.

Keywords: recommendation systems, consumer search, cold start, machine learning

JEL Classification: D83, L86, M31

Suggested Citation

Gardete, Pedro and Santos, Carlos Daniel, No Data? No Problem! A Search-Based Recommendation System With Cold Starts (October 5, 2020). Available at SSRN: https://ssrn.com/abstract=3706925 or http://dx.doi.org/10.2139/ssrn.3706925

Pedro Gardete (Contact Author)

Nova School of Business and Economics ( email )

Rua da Holanda, 1
Carcavelos, Lisbon 2775-405
Portugal

HOME PAGE: http://pedrogardete.com

Carlos Daniel Santos

New University of Lisbon - Nova School of Business and Economics ( email )

Campus de Campolide
Lisbon, 1099-032
Portugal

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
6
Abstract Views
38
PlumX Metrics