The research of Prof. Erekle Pirveli, Professor at the Caucasus School of Business and Director of the Research Center, has been accepted for publication by Applied Economic Analysis—a distinguished journal in the field of applied economics.
Journal Profile: Published by Emerald Publishing (UK), Scopus Q2, article acceptance rate: 2.8%.
The study, based on 15 million observations and employing a hybrid model along with LDA (Latent Dirichlet Allocation) technique, explores the role of news in shaping exchange rates (USD/EUR/GBP).
Title: Unveiling News Impact on Exchange Rates: A Hybrid Model Using NLP and LDA Techniques.
Authors: Teona Shugliashvili (PhD from LMU Munich) and Erekle Pirveli.
Abstract:
Purpose – This study investigates the influence of U.S. dollar-related news on EUR/USD exchange rate using a novel hybrid news-fundamentals-based VAR model applied to 18 years of monthly data.
Design/methodology/approach – Leveraging Latent Dirichlet Allocation (LDA), we identify the top 5 U.S. dollar-related news topics, quantify the attention they receive over time using Shannon’s entropy, and integrate these news-generated metrics with news-constructed economic uncertainty indices and Taylor rule fundamentals into the VAR model. Through impulse-response analysis and forecast error decomposition, we examine how exchange rates react to shocks from the identified U.S. Dollar-related news topics and economic uncertainty captured by the news.
Findings – Our findings reveal that news related to the US dollar and economic uncertainty account for 29% of long-term EUR/USD variation. These results are robust, validated through robustness checks, Granger causality tests, sensitivity analysis, and applying the same model to the GBP/USD exchange rate.
Originality/value – Combining news attention metrics with macroeconomic fundamentals enhances exchange rate identification, outperforming the models that rely solely on the Taylor rule or news variables.
The research was funded by the Shota Rustaveli National Science Foundation of Georgia under the Basic State Research Grant (ID: FR-21-1248).
