RF-GT — Banco de la República's Random Forest Model for Nowcasting Colombian Inflation
Colombia
Banco de la República's July 2025 paper shows a Random Forest model combining Google Trends data with macro indicators nowcasts …
Good practice
Imported
★ 47
★ 47
★ 87
★ 67
A Machine Learning Approach to GDP Nowcasting — Reserve Bank of India's Hybrid ML and Time-Series Model
India · Mumbai · See the India profile · See the Mumbai profile
Evidence: Observational / pre–post Top 62% 53/100 · Ask Evidence Copilot about this practice
Reserve Bank of India economists built a hybrid ML and time-series model — adding financial-market data and an uncertainty index to the bank's GDP nowcast — reporting improved short-horizon accuracy in a 2023 peer-reviewed paper.
Details
- Promoter
- Reserve Bank of India — Department of Economic and Policy Research (DEPR)
- Period
- 2020-2023
- Keywords
- central banking, monetary policy, GDP forecasting, machine learning, nowcasting
Context
India's quarterly GDP estimates are released with a significant lag, which is why the Reserve Bank of India's Department of Economic and Policy Research (DEPR) invested in nowcasting, building on an earlier Dynamic Factor Model (RBI Working Paper WPS(DEPR) 03/2020).
Results
RBI economists Saurabh Ghosh and Abhishek Ranjan tested a hybrid approach adding machine-learning methods, financial-market data and an economic-uncertainty index to the conventional time-series nowcast. The combined approach reported improved nowcast performance over the pure time-series baseline at short horizons, with accuracy declining, as expected, the further out the forecast horizon extends.
Conclusions
The published materials describe this improvement qualitatively rather than through a single, independently audited error-reduction figure, so the evidence should be read as promising internal and peer-reviewed research rather than a fully externally validated production system.
Implementation
- Indicative cost
- Low (< €50k)
- Time to results
- Short (< 1 year)
Commonly funded by
National / regional programmes Horizon Europe
Indicative funding routes for practices of this type — always check each programme's current calls and eligibility rules.
Do you run this practice? Claim it — verified implementers get a public contact pathway and can propose corrections.
Data sources
Where this practice's information was retrieved from, and when.
- C-NAPSE web research — accessed 2026-08-26
- Reserve Bank of India — Department of Economic and Policy Research (DEPR) — accessed 2026-08-26
- SSRN — A Machine Learning (ML) Approach to GDP Nowcasting: An Emerging Market Experience — accessed 2026-08-26
- Bulletin of Monetary Economics and Banking, Vol. 26 (2023) — peer-reviewed publication — accessed 2026-08-26
Similar practices you may find useful
Nowcasting GDP with Machine Learning — the Swiss National Bank's Head-to-Head Test Against 1,100+ Indicators
Switzerland
SNB researchers tested eight machine-learning methods against 1,100+ time series to nowcast Swiss GDP. For the post-2008 period, every ML …
DFROG — De Nederlandsche Bank's Machine-Learning-Tested Nowcasting Model for GDP Growth
Netherlands
DNB's DFROG nowcasting model has tracked Dutch GDP growth in real time since 2024, publishing monthly estimates; a decade-long evaluation …
SSCIF Gets Smarter — Kazakhstan's Central Bank Adds Ridge, Lasso and Elastic-Net Machine Learning to Its Inflation Forecasting System
Kazakhstan
Kazakhstan's central bank added Ridge, Lasso and Elastic-Net machine learning to its inflation forecasting system, cutting pseudo-out-of-sample RMSE 15-19% across …