evidoria

← Back to browse

Good practice Imported

e-Inflation — the Bank of Ghana's In-House AI and Big-Data Nowcasting System for Monetary Policy

Ghana · Accra · See the Ghana profile · See the Accra profile

Evidence: Descriptive / self-reported Top 74% 47/100 · Ask Evidence Copilot about this practice

The Bank of Ghana built an in-house 'e-Inflation' nowcasting methodology and paired it with machine-learning models to sharpen GDP and inflation forecasts ahead of official data, its First Deputy Governor told a national statistics conference in August 2026.

e-Inflation — the Bank of Ghana's In-House AI and Big-Data Nowcasting System for Monetary Policy

Details

Maturity
Established
Promoter
Bank of Ghana
Period
2025–present
Keywords
monetary policy, central banking, inflation forecasting, macroeconomic statistics

Context

In February 2025, Bank of Ghana Governor Dr Johnson Pandit Asiama directed the bank to adopt a more proactive, AI/data-analytics-driven approach to managing inflation.

Activities

Eighteen months later, First Deputy Governor Dr Zakari Mumuni detailed the result at the 4th Annual Statistics and Data Science Conference (27 August 2026): an in-house electronic inflation-nowcasting methodology, 'e-Inflation', sitting alongside the Bank's existing Forecast and Policy Analysis System and Quarterly Projection Model, with machine-learning models complementing standard econometric GDP forecasts and text-mining analytics extracting signals from unstructured information; on the supervisory side, examiners can now validate granular bank data as it arrives rather than waiting on static monthly spreadsheets.

Results

Dr Mumuni said the tools have 'helped the Bank improve the accuracy of its inflation predictions, including forecasts made ahead of official data releases,' independently reported by multiple Ghanaian outlets (Ecofin Agency, MyJoyOnline, B&FT, GhanaWeb, Norvan Reports).

Conclusions

No independently audited accuracy figures have been published, and Mumuni himself cautioned that 'technology can strengthen our intelligence, but it does not remove the need for human judgment.'

Implementation
Indicative cost
Low (< €50k)
Time to results
Medium (1–3 years)
Staffing & skills
Bank of Ghana Research/Statistics department, Text-mining and machine-learning analysts (in-house)

Conditions for success

  • Built in-house rather than outsourced, integrated alongside existing Forecast and Policy Analysis System and Quarterly Projection Model
  • Applied to both monetary-policy nowcasting and bank-supervision data validation

Common failure modes

  • No independently audited accuracy figures published; the Bank's own First Deputy Governor cautions the tool does not remove the need for human judgment

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