Learning user real-time intent for optimal dynamic web page transformation

Amy Wenxuan Ding, Shibo Li, Patrali Chatterjee

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

Many e-commerce websites struggle to turn visitors into real buyers. Understanding online users' real-time intent and dynamic shopping cart choices may have important implications in this realm. This study presents an individual-level, dynamic model with concurrent optimal page adaptation that learns users' real-time, unobserved intent from their online cart choices, then immediately performs optimal Web page adaptation to enhance the conversion of users into buyers. To suggest optimal strategies for concurrent page adaptation, the model analyzes each individual user's browsing behavior, tests the effectiveness of different marketing and Web stimuli, as well as comparison shopping activities at other sites, and performs optimal Web page transformation. Data from an online retailer and a laboratory experiment reveal that concurrent learning of the user's unobserved purchase intent and real-time, intent-based optimal interventions greatly reduce shopping cart abandonment and increase purchase conversions. If the concurrent, intent-based optimal page transformation for the focal site starts after the first page view, shopping cart abandonment declines by 32.4% and purchase conversion improves by 6.9%. The optimal timing for the site to intervene is after three page views, to achieve efficient learning of users' intent and early intervention simultaneously.

Original languageEnglish
Pages (from-to)339-359
Number of pages21
JournalInformation Systems Research
Volume26
Issue number2
DOIs
StatePublished - 1 Jan 2015

Fingerprint

Websites
learning
purchase
Marketing
Dynamic models
electronic business
laboratory experiment
time
World Wide Web
website
stimulus
marketing
Experiments
Shopping
Abandonment
Purchase
Buyers

Keywords

  • Concurrent page adaptation
  • Hidden Markov models
  • Hierarchical Bayes models
  • Optimization
  • Real-time learning
  • Shopping intent
  • Website productivity

Cite this

@article{67d2a40e66b041f88706aed7f00ff85f,
title = "Learning user real-time intent for optimal dynamic web page transformation",
abstract = "Many e-commerce websites struggle to turn visitors into real buyers. Understanding online users' real-time intent and dynamic shopping cart choices may have important implications in this realm. This study presents an individual-level, dynamic model with concurrent optimal page adaptation that learns users' real-time, unobserved intent from their online cart choices, then immediately performs optimal Web page adaptation to enhance the conversion of users into buyers. To suggest optimal strategies for concurrent page adaptation, the model analyzes each individual user's browsing behavior, tests the effectiveness of different marketing and Web stimuli, as well as comparison shopping activities at other sites, and performs optimal Web page transformation. Data from an online retailer and a laboratory experiment reveal that concurrent learning of the user's unobserved purchase intent and real-time, intent-based optimal interventions greatly reduce shopping cart abandonment and increase purchase conversions. If the concurrent, intent-based optimal page transformation for the focal site starts after the first page view, shopping cart abandonment declines by 32.4{\%} and purchase conversion improves by 6.9{\%}. The optimal timing for the site to intervene is after three page views, to achieve efficient learning of users' intent and early intervention simultaneously.",
keywords = "Concurrent page adaptation, Hidden Markov models, Hierarchical Bayes models, Optimization, Real-time learning, Shopping intent, Website productivity",
author = "Ding, {Amy Wenxuan} and Shibo Li and Patrali Chatterjee",
year = "2015",
month = "1",
day = "1",
doi = "10.1287/isre.2015.0568",
language = "English",
volume = "26",
pages = "339--359",
journal = "Information Systems Research",
issn = "1047-7047",
publisher = "INFORMS Institute for Operations Research and the Management Sciences",
number = "2",

}

Learning user real-time intent for optimal dynamic web page transformation. / Ding, Amy Wenxuan; Li, Shibo; Chatterjee, Patrali.

In: Information Systems Research, Vol. 26, No. 2, 01.01.2015, p. 339-359.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Learning user real-time intent for optimal dynamic web page transformation

AU - Ding, Amy Wenxuan

AU - Li, Shibo

AU - Chatterjee, Patrali

PY - 2015/1/1

Y1 - 2015/1/1

N2 - Many e-commerce websites struggle to turn visitors into real buyers. Understanding online users' real-time intent and dynamic shopping cart choices may have important implications in this realm. This study presents an individual-level, dynamic model with concurrent optimal page adaptation that learns users' real-time, unobserved intent from their online cart choices, then immediately performs optimal Web page adaptation to enhance the conversion of users into buyers. To suggest optimal strategies for concurrent page adaptation, the model analyzes each individual user's browsing behavior, tests the effectiveness of different marketing and Web stimuli, as well as comparison shopping activities at other sites, and performs optimal Web page transformation. Data from an online retailer and a laboratory experiment reveal that concurrent learning of the user's unobserved purchase intent and real-time, intent-based optimal interventions greatly reduce shopping cart abandonment and increase purchase conversions. If the concurrent, intent-based optimal page transformation for the focal site starts after the first page view, shopping cart abandonment declines by 32.4% and purchase conversion improves by 6.9%. The optimal timing for the site to intervene is after three page views, to achieve efficient learning of users' intent and early intervention simultaneously.

AB - Many e-commerce websites struggle to turn visitors into real buyers. Understanding online users' real-time intent and dynamic shopping cart choices may have important implications in this realm. This study presents an individual-level, dynamic model with concurrent optimal page adaptation that learns users' real-time, unobserved intent from their online cart choices, then immediately performs optimal Web page adaptation to enhance the conversion of users into buyers. To suggest optimal strategies for concurrent page adaptation, the model analyzes each individual user's browsing behavior, tests the effectiveness of different marketing and Web stimuli, as well as comparison shopping activities at other sites, and performs optimal Web page transformation. Data from an online retailer and a laboratory experiment reveal that concurrent learning of the user's unobserved purchase intent and real-time, intent-based optimal interventions greatly reduce shopping cart abandonment and increase purchase conversions. If the concurrent, intent-based optimal page transformation for the focal site starts after the first page view, shopping cart abandonment declines by 32.4% and purchase conversion improves by 6.9%. The optimal timing for the site to intervene is after three page views, to achieve efficient learning of users' intent and early intervention simultaneously.

KW - Concurrent page adaptation

KW - Hidden Markov models

KW - Hierarchical Bayes models

KW - Optimization

KW - Real-time learning

KW - Shopping intent

KW - Website productivity

UR - http://www.scopus.com/inward/record.url?scp=84959188351&partnerID=8YFLogxK

U2 - 10.1287/isre.2015.0568

DO - 10.1287/isre.2015.0568

M3 - Article

AN - SCOPUS:84959188351

VL - 26

SP - 339

EP - 359

JO - Information Systems Research

JF - Information Systems Research

SN - 1047-7047

IS - 2

ER -