---
title: Machine Learning for GDP
url: https://www.ml-quant.com/papers/repec/snb-snbwpa-2024-06/
site: ML-Quant (https://www.ml-quant.com)
updated: 2026-09-26
license: Summaries CC BY 4.0; links go to the original sources
index: https://www.ml-quant.com/llms.txt
identifier: RePEc:snb:snbwpa:2024-06
source_url: https://econpapers.repec.org/scripts/redir.pf?u=https%3A%2F%2Fwww.snb.ch%2Fen%2Fpublications%2Fresearch%2Fworking-papers%2F2024%2Fworking_paper_2024_06%3Bh%3Drepec%3Asnb%3Asnbwpa%3A2024-06
featured: 2024-06-20
citations: unknown
topic: Macro-Finance & Rates
---


# Machine Learning for GDP

Ridge, elastic net, and SVR machine learning algorithms are the most effective for nowcasting GDP, outperforming other methods by up to 28% in out-of-sample RMSE.

- Source: https://econpapers.repec.org/scripts/redir.pf?u=https%3A%2F%2Fwww.snb.ch%2Fen%2Fpublications%2Fresearch%2Fworking-papers%2F2024%2Fworking_paper_2024_06%3Bh%3Drepec%3Asnb%3Asnbwpa%3A2024-06
- Identifier: RePEc:snb:snbwpa:2024-06
- Released: 2024-06-20
- First featured: Quant Letter No. 54 (2024-06-20): https://www.ml-quant.com/issues/2024-06-20/
- Citations (Semantic Scholar): not tracked
- Published in: not yet
- Topic: Macro-Finance & Rates

## Related

- [Nowcasting GDP with Payments](https://www.ml-quant.com/papers/ssrn/4956446/): The study uses high frequency payment systems data to predict Nigeria's GDP, finding the Mixed Frequency VAR model to be the most precise, with promising results also from the Mixed Data Sampling models combined with principal component analysis.
- [GDP Nowcast Model for India](https://www.ml-quant.com/papers/ssrn/5045024/): The article calls for a reassessment of Indian GDP nowcasting models due to COVID-19 related distortions and the influence of high-frequency indicators.
- [HighFrequency Alternative Data for Japan's GDP Nowcasts](https://www.ml-quant.com/papers/repec/spr-jbuscr-v-19-y-2023-i-2-d-10-1007-s41549-023-00085-1/): The study reveals that credit card data can enhance the accuracy of real-time nowcasting of Japan's GDP, particularly in the early stages of forecasting when traditional data is unavailable.
- [Nowcasting NZ GDP with ML](https://www.ml-quant.com/papers/repec/een-camaaa-2018-47/): The paper reveals that machine learning algorithms are more effective than traditional statistical models in predicting real GDP growth in New Zealand.
- [Outages in Sovereign Bond Markets](https://www.ml-quant.com/papers/ssrn/4860755/): Market disruptions in the euro area futures market result in reduced trading activity, liquidity shortages, and price deviations, with dealers pulling out and clients trading amongst themselves, leading to significant mispricing.
- [Machine Learning for Economic Forecasting: An Application to China's GDP Growth](https://www.ml-quant.com/papers/arxiv/2407.03595/): Machine learning models are more accurate than traditional methods or expert forecasts in predicting China's quarterly GDP growth, especially during stable economic periods.