NLP-Enhanced Inflation Measurement Using BERT and Web Scraping

Berki, Martin; Andicsova, Vanesa; Oravec, Milos

doi:10.3389/frai.2025.1520659

BRIEF RESEARCH REPORT article

Front. Artif. Intell.

Sec. AI in Finance

Volume 8 - 2025 | doi: 10.3389/frai.2025.1520659

This article is part of the Research Topic Applications of AI and Machine Learning in Finance and Economics View all 8 articles

NLP-Enhanced Inflation Measurement Using BERT and Web Scraping

Provisionally accepted

Martin Berki ^*

Vanesa Andicsova

Milos Oravec

Faculty of Electrical Engineering and Informatics, Slovak University of Technology in Bratislava, Bratislava, Slovakia

The final, formatted version of the article will be published soon.

In this research note, we explore the integration of natural language processing (NLP) and web scraping techniques to develop a custom price index for measuring inflation. Using the Harmonized Index of Consumer Prices (HICP) as a benchmark, we created a database of consumer electronics product data through web scraping. Using the BERT model for classification, we achieved a high-performance classification of approximately 10,000 items into COICOP categories, with an accuracy of 94.56 %, macro precision of 79.41 %, and weighted precision of 94.07 % on validation data. Our custom index, particularly with weighted and median methodologies, demonstrated closer alignment with the official HICP while capturing more detailed price fluctuations within the market. Monthly inflation trends revealed variability that reflects price changes in the COICOP 091 category, contrasting with the relative stability of the official HICP.This work provides an alternative perspective on inflation measurement, highlighting the potential of computational approaches to enhance economic analysis.

Keywords: Inflation measurement, Natural Language Processing, Web scraping, BERT, Price index, economic analysis, HICP Frontiers

Received: 31 Oct 2024; Accepted: 24 Mar 2025.

Copyright: © 2025 Berki, Andicsova and Oravec. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

* Correspondence: Martin Berki, Faculty of Electrical Engineering and Informatics, Slovak University of Technology in Bratislava, Bratislava, Slovakia

Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.