Morphing for Consumer Dynamics: Bandits Meet HMM

51 Pages Posted: 16 Dec 2019 Last revised: 14 Feb 2022

See all articles by Gui Liberali

Gui Liberali

Erasmus Research Institute of Management (ERIM); Erasmus University

Alina Ferecatu

Rotterdam School of Management, Erasmus University; Rotterdam School of Management, Erasmus University

Date Written: November 8, 2019

Abstract

Websites are created to help visitors take an action, such as making a purchase or a donation. As visitors browse various webpages, they may take rapid steps towards the action or may bounce away. Websites that can adapt to match such consumer dynamics perform better. However, assessing visitor's changing distance to the action, at each click, and adapting to it in real time is challenging because of the sheer number of design elements that are found in websites, that combine exponentially. We solve this problem by matching latent states to webpage designs, combining recent advances in multi-armed bandit (MAB), website morphing, and hidden Markov models (HMM) literature. We develop a novel dynamic program to explicitly model the trade-off firms face between nudging a visitor to later states along the funnel, and maximizing immediate reward given current estimates of purchase probabilities. We use an HMM to assess visitors' states in real time, and couple it with an MAB model to learn the effectiveness of each design x state combination. We provide a proof-of-concept in two applications. First, we conduct a field study on the MBA website of a major university. Second, we implement our algorithm on a cloud server and test it on an experimental online store.

Keywords: Machine Learning, Electronic Commerce, Website Morphing, Multi-Armed Bandits, Hidden Markov Models (HMM), Retailing

JEL Classification: M31, M30, M37, C61

Suggested Citation

Liberali, Gui and Ferecatu, Alina, Morphing for Consumer Dynamics: Bandits Meet HMM (November 8, 2019). Available at SSRN: https://ssrn.com/abstract=3495518 or http://dx.doi.org/10.2139/ssrn.3495518

Gui Liberali (Contact Author)

Erasmus Research Institute of Management (ERIM) ( email )

P.O. Box 1738
3000 DR Rotterdam
Netherlands

Erasmus University ( email )

Burgemeester Oudlaan 50
3000 DR Rotterdam, Zuid-Holland 3062PA
Netherlands

HOME PAGE: http://guiliberali.org

Alina Ferecatu

Rotterdam School of Management, Erasmus University ( email )

RSM Erasmus University
PO Box 1738
Rotterdam, 3062 PA
Netherlands

Rotterdam School of Management, Erasmus University ( email )

P.O. Box 1738
3000 DR Rotterdam
Netherlands

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

Paper statistics

Downloads
421
Abstract Views
1,483
rank
99,644
PlumX Metrics