Nowcasting GCC GDP: A Machine Learning Solution for Enhanced Non-Oil GDP Prediction
IMF Working Papers, December 19, 2025
Source details
- Canonical URL
- Nowcasting GCC GDP: A Machine Learning Solution for Enhanced Non-Oil GDP Prediction
Other formats
Bibliographic details
- Authors: Greta Polo, Yuan Gao Rollinson, Yevgeniya Korniyenko, Tongfang Yuan
- Published: December 19, 2025
- Series: IMF Working Papers
- DOI: https://doi.org/10.5089/9798229031851.001
Summary / Objective
- Presents a machine learning–based nowcasting framework for estimating quarterly non-oil GDP growth in the Gulf Cooperation Council (GCC) countries.
- Leverages machine learning models tailored to each country to produce timely, sector-specific estimates.
- Aims to enhance granularity, responsiveness, and transparency of short-term forecasts to support faster, data-driven policy decisions across the GCC.
Data and Inputs
- Integrates a broad range of high-frequency indicators—including real activity, financial conditions, trade, and oil-related variables.
- Incorporates high-frequency, cross-border indicators to move beyond single-model methodologies.
Methodology and Innovations
- Tailored data integration strategy that broadens and automates the use of high-frequency indicators.
- Novel application of Shapley value decompositions to:
- Enhance model interpretability.
- Guide iterative selection of predictive indicators.
- Framework flexibility designed to account for:
- The region’s unique economic structures.
- Ongoing reform agendas.
- Spillover effects of oil market volatility on non-oil sectors.
Findings and Contributions
- Advances the nowcasting literature for the MENA region by combining richer high-frequency datasets with country-specific machine learning models.
- Improves sector-specific and short-term estimates of non-oil GDP growth in GCC countries.
- Enhances the transparency and interpretability of model outputs through Shapley value decompositions.
Policy Relevance and Applications
- Enables faster, data-driven policy decisions strengthening economic surveillance and enhancing policy agility across the GCC.
- Suitable for use amid a rapidly evolving global environment where oil market volatility affects non-oil sectors.
Publication and Metadata
- Authors: Greta Polo, Yuan Gao Rollinson, Yevgeniya Korniyenko, Tongfang Yuan
- Date: December 19, 2025
- Series: Working Paper No. 2025/268
- Issue: 268
- Volume: 2025
- Pages: 36
- DOI: https://doi.org/10.5089/9798229031851.001
- Stock No: WPIEA2025268
- ISBN: 9798229031851
- ISSN: 1018-5941
- Subjects: Commodities, Economic forecasting, Oil, Oil prices, Prices
- Keywords: Caribbean, Central America, Central Asia, GCC, Global, growth in the Gulf Cooperation Council, IMF working papers, Machine Learning, machine learning model, Middle East, Non-oil Growth, Nowcasting, nowcasting framework, Nowcasting Gcc, Oil, Oil prices, South America, Southeast Asia
IMF Working Papers — Nowcasting GCC GDP: A Machine Learning Solution for Enhanced Non-Oil GDP Prediction
Content in this bundle
- Working Paper