Institutional Repository of Vilnius University
Žiniatinklio rinkimas siekiant konkurencingos žvalgybos el. prekyboje: rinkos įžvalgų automatizavimas /
Abstract
dc:descriptionThis thesis explores the application of large language models (LLMs) to automate market analysis in ecommerce. The main objective of the study is to implement and evaluate a solution that uses LLMs together with the Crawl4AI library to automatically extract structured information (product names and prices) from ecommerce websites. During the experiment, a web scraping tool was implemented and tested with three different models: gpt-4.1-nano, gpt-4.1-mini, and deepseek-qchat. The tool achieved exceptionally high accuracy rates—by using dynamically adapted prompts, it reached up to 100% recall on real ecommerce websites.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2025
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Motiejūnas, Ugnius,
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD239031894&prefLang=en_US