evidoria

← Back to browse

Good practice Imported

Nowcasting Kenya's GDP — the Central Bank's IMF-Assisted Real-Time Growth-Tracking Model

Kenya · Nairobi · See the Kenya profile · See the Nairobi profile

Evidence: Observational / pre–post Top 32% 67/100 · Ask Evidence Copilot about this practice

An IMF-assisted nowcasting model gives Kenya's central bank weekly-updated GDP growth estimates from mobile-money, electricity, trade and remittance data, cutting the usual three-month lag and beating prior CBK and IMF forecasts out-of-sample.

~3 weeks
Mobile-money data availability lag (2023-present)
~40 days, about half the official release lag
Other indicator (trade, electricity, tourism) data availability lag (2023-present)
Nowcasting Kenya's GDP — the Central Bank's IMF-Assisted Real-Time Growth-Tracking Model

Details

Maturity
Established
Promoter
Central Bank of Kenya
Period
2023–present
Keywords
monetary policy, central banking, GDP forecasting, macroeconomic statistics

Context

Kenya's official GDP figures are published more than three months after each quarter ends, too slow to guide the central bank's real-time interest-rate decisions.

Objectives

Build a nowcasting framework that continuously updates a near-term GDP growth estimate from high-frequency data, closing the lag in official statistics.

Activities

Following an IMF Monetary and Capital Markets Department technical-assistance mission to Nairobi in April 2023, the Central Bank of Kenya built a model that ingests mobile-money transaction volumes (available within about three weeks), then remittances, trade, money-supply, tourism and electricity data (available within roughly 40 days, around half the time of the official release).

Results

IMF Working Paper 2026/032 reports the nowcasting framework 'performs well out-of-sample compared to alternative forecasts by the CBK and the IMF'. Key swings in the nowcast since 2024 have come from electricity and vehicle-production data, digital-money flows, and goods trade.

Conclusions

The model gives the CBK a real-time growth signal roughly twice as fast as the official release and has out-performed prior in-house forecasts, though a 2024 IMF report flagged that underlying business-survey data quality still needs strengthening for the nowcast to stay reliable.

Implementation
Indicative cost
Low (< €50k) — A statistical/econometric model built on existing administrative and mobile-money data rather than new data collection or heavy compute infrastructure, consistent with a low direct cost once IMF technical assistance is factored as external support.
Time to results
Medium (1–3 years) — Developed from an April 2023 IMF technical-assistance mission through to a 2026 published working paper, with the nowcast now feeding the Bank's Monetary Policy Committee briefings on an ongoing basis.
Staffing & skills
Central Bank of Kenya research/statistics staff, IMF Monetary and Capital Markets Department technical-assistance team

Conditions for success

  • Access to high-frequency proxy data (mobile-money, electricity, trade, remittances) available faster than official GDP statistics
  • External technical assistance (IMF) for model design and validation
  • Ongoing strengthening of underlying business surveys to keep nowcast inputs reliable

Common failure modes

  • The IMF's own 2024 Technical Assistance Report flagged that Kenya's underlying business surveys needed strengthening for the nowcast to stay reliable, work described as still ongoing

Where it fits

Governance type
national central bank
Scale
national
Income level
lower-middle-income

Commonly funded by

National / regional programmes

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.

Attachments

Similar practices you may find useful