Measuring economic outlook in the news timely and efficiently
By: Elliot Beck , Franziska Eckert , Linus Kühne and more
Potential Business Impact:
Predicts economy growth better using news.
We introduce a novel indicator that combines machine learning and large language models with traditional statistical methods to track sentiment regarding the economic outlook in Swiss news. The indicator is interpretable and timely, and it significantly improves the accuracy of GDP growth forecasts. Our approach is resource-efficient, modular, and offers a way of benefitting from state-of-the-art large language models even if data are proprietary and cannot be stored or analyzed on external infrastructure - a restriction faced by many central banks and public institutions.
Similar Papers
Geopolitics, Geoeconomics and Risk:A Machine Learning Approach
Machine Learning (Stat)
News helps predict country money risk better.
Forecasting U.S. equity market volatility with attention and sentiment to the economy
General Finance
Predicts stock price swings using social media.
Macroeconomic Forecasting and Machine Learning
Econometrics
Predicts future money problems more accurately.