{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T05:11:46Z","timestamp":1785906706826,"version":"3.56.0"},"reference-count":57,"publisher":"Emerald","issue":"11","license":[{"start":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T00:00:00Z","timestamp":1657843200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.emerald.com\/insight\/site-policies"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["K"],"published-print":{"date-parts":[[2023,11,9]]},"abstract":"<jats:sec><jats:title content-type=\"abstract-subheading\">Purpose<\/jats:title><jats:p>Purchase conversion prediction aims to improve user experience and convert visitors into real buyers to drive sales of firms; however, the total conversion rate is low, especially for e-retailers. To date, little is known about how e-retailers can scientifically detect users' intents within a purchase conversion funnel during their ongoing sessions and strategically optimize real-time marketing tactics corresponding to dynamic intent states. This study mainly aims to detect a real-time state of the conversion funnel based on graph theory, which refers to a five-class classification problem in the overt real-time choice decisions (RTCDs)\u2014click, tag-to-wishlist, add-to-cart, remove-from-cart and purchase\u2014during an ongoing session.<\/jats:p><\/jats:sec><jats:sec><jats:title content-type=\"abstract-subheading\">Design\/methodology\/approach<\/jats:title><jats:p>The authors propose a novel graph-theoretic framework to detect different states of the conversion funnel by identifying a user's unobserved mindset revealed from their navigation process graph, namely clickstream graph. First, the raw clickstream data are identified into individual sessions based on a 30-min time-out heuristic approach. Then, the authors convert each session into a sequence of temporal item-level clickstream graphs and conduct a temporal graph feature engineering according to the basic, single-, dyadic- and triadic-node and global characteristics. Furthermore, the synthetic minority oversampling technique is adopted to address with the problem of classifying imbalanced data. Finally, the authors train and test the proposed approach with several popular artificial intelligence algorithms.<\/jats:p><\/jats:sec><jats:sec><jats:title content-type=\"abstract-subheading\">Findings<\/jats:title><jats:p>The graph-theoretic approach validates that users' latent intent states within the conversion funnel can be interpreted as time-varying natures of their online graph footprints. In particular, the experimental results indicate that the graph-theoretic feature-oriented models achieve a substantial improvement of over 27% in line with the macro-average and micro-average area under the precision-recall curve, as compared to the conventional ones. In addition, the top five informative graph features for RTCDs are found to be Transitivity, Edge, Node, Degree and Reciprocity. In view of interpretability, the basic, single-, dyadic- and triadic-node and global characteristics of clickstream graphs have their specific advantages.<\/jats:p><\/jats:sec><jats:sec><jats:title content-type=\"abstract-subheading\">Practical implications<\/jats:title><jats:p>The findings suggest that the temporal graph-theoretic approach can form an efficient and powerful AI-based real-time intent detecting decision-support system. Different levels of graph features have their specific interpretability on RTCDs from the perspectives of consumer behavior and psychology, which provides a theoretical basis for the design of computer information systems and the optimization of the ongoing session intervention or recommendation in e-commerce.<\/jats:p><\/jats:sec><jats:sec><jats:title content-type=\"abstract-subheading\">Originality\/value<\/jats:title><jats:p>To the best of the authors' knowledge, this is the first study to apply clickstream graphs and real-time decision choices in conversion prediction and detection. Most studies have only meditated on a binary classification problem, while this study applies a graph-theoretic approach in a five-class classification problem. In addition, this study constructs temporal item-level graphs to represent the original structure of clickstream session data based on graph theory. The time-varying characteristics of the proposed approach enhance the performance of purchase conversion detection during an ongoing session.<\/jats:p><\/jats:sec>","DOI":"10.1108\/k-06-2021-0473","type":"journal-article","created":{"date-parts":[[2022,7,14]],"date-time":"2022-07-14T12:51:46Z","timestamp":1657803106000},"page":"5139-5163","source":"Crossref","is-referenced-by-count":7,"title":["Graph-theoretic approach to detecting real-time intents within purchase conversion funnel using clickstream data"],"prefix":"10.1108","volume":"52","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6273-6695","authenticated-orcid":false,"given":"Hongming","family":"Gao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1133-4930","authenticated-orcid":false,"given":"Hongwei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1646-4152","authenticated-orcid":false,"given":"Weizhen","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6309-4196","authenticated-orcid":false,"given":"Chunfeng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"140","published-online":{"date-parts":[[2022,7,15]]},"reference":[{"issue":"3","key":"key2023110803373855000_ref001","doi-asserted-by":"crossref","first-page":"370","DOI":"10.1002\/wics.84","article-title":"Multicollinearity","volume":"2","year":"2010","journal-title":"Wiley Interdisciplinary Reviews: Computational Statistics"},{"issue":"5","key":"key2023110803373855000_ref002","doi-asserted-by":"crossref","first-page":"985","DOI":"10.1108\/K-06-2017-0196","article-title":"Recommender systems: a systematic review of the state of the art literature and suggestions for future research","volume":"47","year":"2018","journal-title":"Kybernetes"},{"key":"key2023110803373855000_ref003","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1016\/j.eswa.2017.10.046","article-title":"Changing perspectives: using graph metrics to predict purchase probabilities","volume":"94","year":"2018","journal-title":"Expert Systems with Applications"},{"issue":"1","key":"key2023110803373855000_ref004","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1287\/isre.2016.0655","article-title":"Providing a window of opportunity for converting eStore visitors","volume":"28","year":"2017","journal-title":"Information Systems Research"},{"issue":"1","key":"key2023110803373855000_ref005","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","year":"2001","journal-title":"Machine Learning"},{"issue":"5","key":"key2023110803373855000_ref006","doi-asserted-by":"crossref","first-page":"693","DOI":"10.1287\/mksc.2016.0977","article-title":"Zooming in on choice: how do consumers search for cameras online?","volume":"35","year":"2016","journal-title":"Marketing Science"},{"issue":"1","key":"key2023110803373855000_ref007","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1016\/j.intmar.2008.10.004","article-title":"Click here for Internet insight: advances in clickstream data analysis in marketing","volume":"23","year":"2009","journal-title":"Journal of Interactive Marketing"},{"issue":"1","key":"key2023110803373855000_ref008","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1111\/j.1467-839X.2007.00241.x","article-title":"Social network analysis: a methodological introduction","volume":"11","year":"2008","journal-title":"Asian Journal of Social Psychology"},{"issue":"1","key":"key2023110803373855000_ref009","first-page":"46","article-title":"Hypermediation: commerce as clickstream","volume":"78","year":"2000","journal-title":"Harvard Business Review"},{"issue":"4","key":"key2023110803373855000_ref010","doi-asserted-by":"crossref","first-page":"435","DOI":"10.1080\/02664769922322","article-title":"Robustness of partial least-squares method for estimating latent variable quality structures","volume":"26","year":"1999","journal-title":"Journal of Applied Statistics"},{"issue":"2","key":"key2023110803373855000_ref011","doi-asserted-by":"crossref","first-page":"244","DOI":"10.1086\/376803","article-title":"The influence of macro-level motives on consideration set composition in novel purchase situations","volume":"30","year":"2003","journal-title":"Journal of Consumer Research"},{"key":"key2023110803373855000_ref012","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: synthetic minority over-sampling technique","volume":"16","year":"2002","journal-title":"Journal of Artificial Intelligence Research"},{"issue":"2","key":"key2023110803373855000_ref013","doi-asserted-by":"crossref","first-page":"339","DOI":"10.1287\/isre.2015.0568","article-title":"Learning user real-time intent for optimal dynamic web page transformation","volume":"26","year":"2015","journal-title":"Information Systems Research"},{"issue":"9","key":"key2023110803373855000_ref014","first-page":"17","article-title":"From marketing mix to e-marketing mix: a literature overview and classification","volume":"4","year":"2009","journal-title":"International Journal of Business and Management"},{"issue":"2","key":"key2023110803373855000_ref015","doi-asserted-by":"crossref","first-page":"173","DOI":"10.2753\/MIS0742-1222290207","article-title":"A data-driven approach to measure web site navigability","volume":"29","year":"2012","journal-title":"Journal of Management Information Systems"},{"issue":"3","key":"key2023110803373855000_ref016","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1016\/0378-8733(78)90021-7","article-title":"Centrality in social networks conceptual clarification","volume":"1","year":"1978","journal-title":"Social Networks"},{"issue":"1","key":"key2023110803373855000_ref017","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1002\/bdm.2199","article-title":"Choosing what to choose from: preference for inclusion over exclusion when constructing consideration sets from large choice sets","volume":"34","year":"2021","journal-title":"Journal of Behavioral Decision Making"},{"key":"key2023110803373855000_ref018","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1145\/956750.956815","article-title":"A web page prediction model based on click-stream tree representation of user behavior","year":"2003"},{"issue":"2","key":"key2023110803373855000_ref019","doi-asserted-by":"crossref","first-page":"497","DOI":"10.25300\/MISQ\/2014\/38.2.08","article-title":"The effects of Web personalization on user attitude and behavior: an integration of the elaboration likelihood model and consumer search theory","volume":"38","year":"2014","journal-title":"MIS Quarterly"},{"issue":"3","key":"key2023110803373855000_ref020","doi-asserted-by":"crossref","first-page":"492","DOI":"10.1086\/224954","article-title":"A method for detecting structure in sociometric data","volume":"76","year":"1970","journal-title":"American Journal of Sociology"},{"issue":"3","key":"key2023110803373855000_ref021","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1016\/j.physrep.2012.03.001","article-title":"Temporal networks","volume":"519","year":"2012","journal-title":"Physics Reports"},{"issue":"5360","key":"key2023110803373855000_ref022","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1126\/science.280.5360.95","article-title":"Strong regularities in world wide web surfing","volume":"280","year":"1998","journal-title":"Science"},{"issue":"5","key":"key2023110803373855000_ref023","doi-asserted-by":"crossref","first-page":"844","DOI":"10.1287\/mksc.2020.1279","article-title":"Understanding large-scale dynamic purchase behavior","volume":"40","year":"2021","journal-title":"Marketing Science"},{"issue":"3","key":"key2023110803373855000_ref024","doi-asserted-by":"crossref","first-page":"121","DOI":"10.2753\/JEC1086-4415100305","article-title":"Predicting on-line task completion with clickstream complexity measures: a graph-based approach","volume":"10","year":"2006","journal-title":"International Journal of Electronic Commerce"},{"issue":"3","key":"key2023110803373855000_ref025","first-page":"895","article-title":"On the spillover effects of online product reviews on purchases: evidence from clickstream data","volume":"32","year":"2020","journal-title":"Information Systems Research"},{"issue":"4","key":"key2023110803373855000_ref026","doi-asserted-by":"crossref","first-page":"1203","DOI":"10.1287\/isre.2019.0859","article-title":"When and how to leverage E-commerce cart targeting: the relative and moderated effects of scarcity and price incentives with a two-stage field experiment and causal forest optimization","volume":"30","year":"2019","journal-title":"Information Systems Research"},{"issue":"5","key":"key2023110803373855000_ref027","doi-asserted-by":"crossref","first-page":"761","DOI":"10.1006\/ijhc.2001.0505","article-title":"Graphic and numerical methods to assess navigation in hypertext","volume":"55","year":"2001","journal-title":"International Journal of Human-Computer Studies"},{"issue":"1","key":"key2023110803373855000_ref028","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1287\/mksc.22.1.58.12849","article-title":"Price uncertainty and consumer search: a structural model of consideration set formation","volume":"22","year":"2003","journal-title":"Marketing Science"},{"key":"key2023110803373855000_ref029","volume-title":"Applied Logistic Regression Analysis","year":"2002"},{"issue":"1","key":"key2023110803373855000_ref030","first-page":"1","article-title":"A comparison of random forest and its Gini importance with standard chemometric methods for the feature selection and classification of spectral data","volume":"10","year":"2009","journal-title":"BMC Bioinformatics"},{"issue":"1-2","key":"key2023110803373855000_ref031","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1207\/S15327663JCP13-1&2_03","article-title":"Buying, searching, or browsing: differentiating between online shoppers using in-store navigational clickstream","volume":"13","year":"2003","journal-title":"Journal of Consumer Psychology"},{"issue":"1","key":"key2023110803373855000_ref032","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1002\/dir.10074","article-title":"Capturing evolving visit behavior in clickstream data","volume":"18","year":"2004","journal-title":"Journal of Interactive Marketing"},{"issue":"3","key":"key2023110803373855000_ref033","doi-asserted-by":"crossref","first-page":"326","DOI":"10.1287\/mnsc.1040.0153","article-title":"Dynamic conversion behavior at e-commerce sites","volume":"50","year":"2004","journal-title":"Management Science"},{"key":"key2023110803373855000_ref034","doi-asserted-by":"publisher","DOI":"10.1016\/j.elerap.2019.100836","article-title":"Will this session end with a purchase? Inferring current purchase intent of anonymous visitors","volume":"34","year":"2019","journal-title":"Electronic Commerce Research and Applications"},{"key":"key2023110803373855000_ref035","unstructured":"Monetate (2019), \u201cEcommerce quarterly benchmarks Q2 2019\u201d, available at: https:\/\/info.monetate.com\/rs\/092-TQN-434\/images\/Q2%20Monetate%20Ecommerce%20Benchmarks.pdf (accessed 8 October 2019)."},{"key":"key2023110803373855000_ref036","unstructured":"Montgomery, A.L. (1999), \u201cUsing clickstream data to predict WWW usage\u201d, available at: www.andrew.cmu.edu\/user\/alm3\/papers\/predicting%20www%20usage.pdf (accessed 8 October 2019)."},{"issue":"4","key":"key2023110803373855000_ref037","doi-asserted-by":"crossref","first-page":"579","DOI":"10.1287\/mksc.1040.0073","article-title":"Modeling online browsing and path analysis using clickstream data","volume":"23","year":"2004","journal-title":"Marketing Science"},{"issue":"3","key":"key2023110803373855000_ref038","doi-asserted-by":"crossref","first-page":"521","DOI":"10.1287\/mksc.1120.0713","article-title":"Mine your own business: market-structure surveillance through text mining","volume":"31","year":"2012","journal-title":"Marketing Science"},{"issue":"3","key":"key2023110803373855000_ref039","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1177\/002224377100800301","article-title":"Stages of consumer decision making","volume":"8","year":"1971","journal-title":"Journal of Marketing Research"},{"issue":"1","key":"key2023110803373855000_ref040","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1177\/1470785320972526","article-title":"Predicting online shopping cart abandonment with machine learning approaches","volume":"64","year":"2022","journal-title":"International Journal of Market Research"},{"issue":"5","key":"key2023110803373855000_ref041","doi-asserted-by":"crossref","first-page":"788","DOI":"10.1108\/K-09-2014-0184","article-title":"A comparison of the different versions of popular technology acceptance models","volume":"44","year":"2015","journal-title":"Kybernetes"},{"issue":"3","key":"key2023110803373855000_ref042","article-title":"The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets","volume":"10","year":"2015","journal-title":"PloS One"},{"issue":"10","key":"key2023110803373855000_ref043","doi-asserted-by":"crossref","first-page":"6893","DOI":"10.1007\/s00521-018-3523-0","article-title":"Real-time prediction of online shoppers' purchasing intention using multilayer perceptron and LSTM recurrent neural networks","volume":"31","year":"2019","journal-title":"Neural Computing and Applications"},{"issue":"3","key":"key2023110803373855000_ref044","doi-asserted-by":"crossref","first-page":"611","DOI":"10.1198\/106186008X344522","article-title":"A bias correction algorithm for the Gini variable importance measure in classification trees","volume":"17","year":"2008","journal-title":"Journal of Computational and Graphical Statistics"},{"issue":"3","key":"key2023110803373855000_ref045","doi-asserted-by":"crossref","first-page":"220","DOI":"10.1504\/IJEB.2014.063036","article-title":"Dynamic identification of anonymous consumers' visit goals using clickstream","volume":"11","year":"2014","journal-title":"International Journal of Electronic Business"},{"issue":"2","key":"key2023110803373855000_ref046","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1287\/ijoc.15.2.171.14445","article-title":"A framework for the evaluation of session reconstruction heuristics in web-usage analysis","volume":"15","year":"2003","journal-title":"Informs Journal on Computing"},{"issue":"1","key":"key2023110803373855000_ref047","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.elerap.2014.10.002","article-title":"A method for discovering clusters of e-commerce interest patterns using click-stream data","volume":"14","year":"2015","journal-title":"Electronic Commerce Research and Applications"},{"issue":"1","key":"key2023110803373855000_ref048","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1287\/isre.2019.0877","article-title":"Trade-offs in online advertising: advertising effectiveness and annoyance dynamics across the purchase funnel","volume":"31","year":"2020","journal-title":"Information Systems Research"},{"key":"key2023110803373855000_ref049","first-page":"1","article-title":"Predicting shopping behavior with mixture of RNNs","year":"2017"},{"key":"key2023110803373855000_ref050","first-page":"185","article-title":"Enabling scalable online personalization on the web","year":"2000"},{"key":"key2023110803373855000_ref051","first-page":"225","article-title":"Unsupervised clickstream clustering for user behavior analysis","year":"2016"},{"key":"key2023110803373855000_ref052","volume-title":"Social Network Analysis: Methods and Applications","year":"1994"},{"key":"key2023110803373855000_ref053","unstructured":"Wei, R., Wang, J., Jia, W. and Wei, M.R. (2018), \u201cPackage \u2018multiROC\u2019\u201d, Release 1.1.1. version 1.1.1, available at: https:\/\/cran.r-project.org\/web\/packages\/multiROC\/index.html (accessed 17 October 2019)."},{"issue":"1","key":"key2023110803373855000_ref054","doi-asserted-by":"crossref","first-page":"137","DOI":"10.2307\/25148784","article-title":"E-commerce product recommendation agents: use, characteristics, and impact","volume":"31","year":"2007","journal-title":"MIS Quarterly"},{"issue":"2","key":"key2023110803373855000_ref055","doi-asserted-by":"crossref","first-page":"413","DOI":"10.1287\/isre.2017.0695","article-title":"Designing for diagnosticity and serendipity: an investigation of social product-search mechanisms","volume":"28","year":"2017","journal-title":"Information Systems Research"},{"issue":"1","key":"key2023110803373855000_ref056","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1287\/isre.1120.0464","article-title":"Social ties and user content generation: evidence from Flickr","volume":"24","year":"2013","journal-title":"Information Systems Research"},{"issue":"1","key":"key2023110803373855000_ref057","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1108\/APJML-08-2019-0497","article-title":"Identifying market structure to monitor product competition using a consumer-behavior-based intelligence model","volume":"33","year":"2020","journal-title":"Asia Pacific Journal of Marketing and Logistics"}],"container-title":["Kybernetes"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/K-06-2021-0473\/full\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/K-06-2021-0473\/full\/html","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T21:48:51Z","timestamp":1753393731000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.emerald.com\/k\/article\/52\/11\/5139-5163\/459266"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,15]]},"references-count":57,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2022,7,15]]},"published-print":{"date-parts":[[2023,11,9]]}},"alternative-id":["10.1108\/K-06-2021-0473"],"URL":"https:\/\/doi.org\/10.1108\/k-06-2021-0473","relation":{},"ISSN":["0368-492X"],"issn-type":[{"value":"0368-492X","type":"print"}],"subject":[],"published":{"date-parts":[[2022,7,15]]}}}