Deepening digital user understanding through large language model analysis of clickstream-based segments.
Saved in:
| Title: | Deepening digital user understanding through large language model analysis of clickstream-based segments. |
|---|---|
| Authors: | Wasilewski, Adam1 (AUTHOR), Chawla, Yash1 (AUTHOR) yash.chawla@pwr.edu.pl, Kozuljevic, Nikola2 (AUTHOR) |
| Source: | Telematics & Informatics. Jan2026, Vol. 104, pN.PAG-N.PAG. 1p. |
| Subjects: | Consumer preferences, Consumer behavior, Generative artificial intelligence, Language models, Market segmentation, Digital footprint, Digital technology |
| Abstract: | Effective digital platform strategies often depend on a deep understanding of user behavior. Specifically within e-commerce, analyzing clickstream data through machine learning allows users to be categorized into distinct segments based on their online interactions. This research explores the potential of large language models (LLMs) to extract granular insights from these customer segments. Unlike traditional methods, LLMs may possess a greater ability to uncover latent patterns within user preferences, needs, and motivations as reflected in interaction data. This study demonstrates, within an e-commerce context, the effectiveness of integrating clickstream segmentation with LLMs to generate actionable recommendations for personalized marketing campaigns, innovative product development, and improved customer service. The research indicates areas of practical application for this LLM-based approach, and the results show the great potential of such tools in e-commerce analytics, including getting to understand user behaviors and pre-determining personalization directions. By harnessing the power of LLMs, companies can gain a deeper understanding of user behavior within their specific domain, identify untapped opportunities, and tailor their offerings. Ultimately, this research contributes to advancing e-commerce analysis methodologies and offers insights potentially applicable to understanding user interactions on other digital platforms, enabling organizations to optimize operations and foster customer loyalty. • LLMs integrated with clickstream segmentation allow for uncovering customer preferences and needs, enhancing e-commerce insights. • The metrics generated by Generative AI need additional evaluation for consistency and relevance in customer analysis. • The structure of responses determines the consistency and repeatability of e-commerce customer behavior assessments. [ABSTRACT FROM AUTHOR] |
| Copyright of Telematics & Informatics is the property of Pergamon Press - An Imprint of Elsevier Science and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
Be the first to leave a comment!
