Course overview
This advanced professional workshop equips central bank supervisors, prudential regulators, financial-sector oversight teams and supervisory technology specialists with the knowledge and practical methods to apply artificial intelligence, advanced analytics and digital supervisory systems to modern banking supervision.
The programme explores how AI and SupTech can strengthen off-site surveillance, risk-based supervision, early-warning systems, regulatory reporting, prudential analysis, conduct monitoring and supervisory decision-making. Participants learn how to analyse large volumes of regulatory returns, detect emerging financial vulnerabilities, identify anomalies, prioritise supervisory inspections and improve the timeliness and consistency of regulatory oversight.
The workshop integrates machine learning, natural language processing, automated data validation, supervisory dashboards, network analysis and responsible generative AI applications. It emphasises explainability, data governance, cybersecurity, model validation, confidentiality and human accountability—ensuring that AI supports supervisory judgement rather than replacing statutory authority or professional oversight.
Course objectives
- Design AI-enabled supervisory workflows for analysing regulatory returns, prudential indicators, financial statements and supervisory submissions.
- Establish effective SupTech governance arrangements covering model validation, data confidentiality, explainability, cybersecurity, human oversight and supervisory accountability.
- Develop risk-based supervisory dashboards, early-warning indicators and institution-level risk profiles to support the prioritisation of supervisory examinations.
- Use natural language processing and generative AI to review regulatory documents, board minutes, audit findings, risk disclosures and compliance submissions.
- Apply machine learning, anomaly detection and predictive analytics to identify emerging credit, liquidity, capital adequacy, operational and systemic risks.
Who should attend
Central bank supervisors, prudential regulators, banking supervision officers, off-site surveillance analysts, on-site examination teams, financial stability analysts, regulatory reporting specialists, risk-based supervision teams, AML/CFT supervisors, market conduct regulators, supervisory technology teams, data scientists, financial sector policy advisors and senior officials responsible for digital supervisory transformation.
Course content
- Module 1: Foundations of AI-Powered Banking Supervision and SupTech Concepts and evolution of supervisory technology; differences between SupTech, RegTech and conventional supervisory automation; applications across prudential supervision, conduct superv
- Module 2: Digital Supervisory Data Architecture and Regulatory Reporting Designing data-driven supervisory workflows; integrating regulatory returns, financial statements, capital adequacy reports, liquidity returns, credit exposures and loan-level infor
- Module 3: AI-Based Prudential Monitoring and Bank Risk Profiling Analysing capital adequacy, asset quality, management quality, earnings, liquidity and sensitivity to market risk; calculating supervisory ratios; developing composite risk indicators; dete
- Module 4: Machine Learning for Credit Risk and Asset Quality Surveillance Using supervised and unsupervised machine learning to analyse non-performing loans, loan concentrations, arrears, credit migration and provisioning trends; identifying unusual chan
- Module 5: AI-Enabled Liquidity, Capital and Solvency Monitoring Monitoring liquidity coverage, funding concentrations, deposit withdrawals, maturity mismatches and capital adequacy indicators; detecting unusual deposit movements and funding pressures; as
- Module 6: Anomaly Detection and Automated Regulatory Return Validation Applying statistical rules, machine learning and anomaly detection to identify inconsistent regulatory submissions, unusual transactions, unexplained financial movements, missing disc
- Module 7: Natural Language Processing for Supervisory Document Intelligence Using NLP to extract information from annual reports, financial statements, board minutes, internal audit reports, risk disclosures, inspection reports and management responses;
- Module 8: Generative AI and Large Language Models in Supervision Applying generative AI to summarise regulatory submissions, compare disclosures, retrieve relevant regulatory provisions, draft preliminary examination summaries and organise evidence for s
- Module 9: AI-Powered Risk-Based Supervisory Planning Combining quantitative risk indicators, qualitative assessments, previous inspection findings and supervisory judgement to rank institutions and determine examination priorities. Developing risk heat m
- Module 10: SupTech for On-Site Examinations and Off-Site Surveillance Integrating off-site monitoring with on-site supervisory examinations; using automated analysis to identify institutions, business lines and control functions requiring deeper review;
- Module 11: Financial Crime, AML/CFT and Network Analytics Applying data analytics to identify suspicious transaction patterns, related-party exposures, interconnected entities, unusual payment networks and potential financial crime risks. Using graph ana
- Module 12: AI for Governance, Conduct and Consumer Protection Supervision Analysing governance disclosures, board effectiveness indicators, complaints, product pricing, customer treatment, sales practices and potential mis-selling. Using text analytics t
- Module 13: Supervisory Dashboards, Early-Warning Systems and Predictive Analytics Developing interactive dashboards that consolidate prudential ratios, supervisory ratings, regulatory breaches, risk trends and emerging vulnerabilities. Using time-series
- Module 14: SupTech Governance, Cybersecurity and Responsible AI Establishing governance arrangements for AI-assisted supervision; model inventories, validation standards, audit trails, access controls, data privacy, confidentiality and retention requirem
- Module 15: Integrated AI-Powered Banking Supervision Capstone Participants develop a prototype supervisory analytics workflow using a realistic or synthetic banking dataset. The exercise includes regulatory data validation, calculation of prudential indi
General notes
- Practical Exercises and Case Studies Automated validation of bank regulatory returns, detection of inconsistencies in capital adequacy and liquidity reports, identification of unusual non-performing loan movements, comparison of prudential indicators across peer banks, machine-learning-based early warning of deteriorating bank performance, detection of abnormal deposit withdrawals and funding concentration, AI-assisted review of annual reports and board minutes, extraction and classification of regulatory compliance findings, analysis of related-party exposures using entity and network analytics, prioritisation of on-site inspections using risk indicators, development of a supervisory risk dashboard, evaluation of false positives and false negatives in anomaly detection, AI-assisted comparison of regulatory requirements with bank disclosures, monitoring remediation of examination findings, and preparation of a supervisory risk assessment briefing.
- Practical Outputs and Diliverables:AI-powered banking supervision use-case assessment framework, supervisory data inventory and regulatory reporting quality checklist, automated regulatory return validation rules and exception report, prudential indicator calculation and peer-benchmarking template, AI-assisted bank risk profiling framework, credit quality and liquidity early-warning indicator model, anomaly detection and supervisory alert prioritisation framework, NLP-based supervisory document review workflow, regulatory compliance evidence extraction and review template, risk-based supervisory examination prioritisation matrix, supervisory risk dashboard covering capital adequacy, asset quality, earnings, liquidity and emerging vulnerabilities, model validation and performance assessment scorecard, responsible AI and SupTech governance checklist, supervisory action tracking and remediation monitoring framework, capstone supervisory risk assessment report with evidence-based recommendations
- Enterprise Tools for AI-Powered Banking Supervision and SupTech Training Databricks, Apache Kafka, Apache Spark, Informatica, Microsoft Purview, Collibra, Azure Machine Learning, Amazon SageMaker, Google Vertex AI, MLflow, Kubeflow, Azure AI Foundry, Amazon Bedrock, LangChain, LlamaIndex, Elasticsearch, OpenSearch, Neo4j, TigerGraph, Apigee, MuleSoft, Azure API Management, Docker, Kubernetes, Red Hat OpenShift, Microsoft Entra ID, CyberArk, HashiCorp Vault, Microsoft Sentinel, Splunk Enterprise Security, Camunda, ServiceNow.
- aster advanced econometrics and time-series analysis for central bank applications, including inflation forecasting, VAR models, cointegration, Bayesian estimation, monetary policy transmission and AI-enhanced forecasting.
- : Time-Series Analysis for Economists, Monetary Policy Econometrics, Central Bank Forecasting Models, VAR and Bayesian VAR Training, Econometric Modelling for Inflation, Macroeconomic Forecasting Training, Cointegration and Error-Correction Modelling, Applied Econometrics for Central Banks, AI and Econometric Forecasting.
- Research references - Bank for International Settlements (BIS): Economic Modelling and Forecasting Practices in Central Banks. Explains the role of multiple macroeconomic models—including VAR, state-space, Bayesian, semi-structural and DSGE approaches—in policy analysis and forecasting. Bank for International Settlements - BIS, March 2026: BISTRO: A General-Purpose Oracle for Macroeconomic Time Series. Examines emerging AI-based time-series forecasting and its potential use alongside traditional econometric benchmarks. Bank for International Settlements +1 - IMF: Bayesian VARs: A Survey of the Recent Literature. Provides background on Bayesian VAR estimation, forecasting and structural analysis. International Monetary Fund - Journal of Economic Surveys: Central Bank Forecasting: A Survey. Reviews forecasting practices and developments across major central banks.
Frequently asked questions
1. 1. Who should attend this workshop?
The workshop is designed for central bank economists, monetary policy researchers, quantitative analysts, macroeconomic modellers and financial stability specialists who use empirical models for economic forecasting and policy analysis.
2. 2. What econometric methods are covered?
Participants study ARIMA and SARIMA, VAR and structural VAR, cointegration, error-correction models, Bayesian VAR, state-space models, Kalman filtering, GARCH, local projections, dynamic factor models, structural-break analysis and selected machine-learning approaches.
3. 3. Does the course focus on monetary policy applications?
Yes. Practical applications include inflation forecasting, policy-rate transmission, exchange-rate pass-through, output-gap estimation, money demand, economic shocks, financial volatility and the evaluation of alternative policy scenarios.
4. 4. Is programming required?
A background in statistics, economics or quantitative analysis is recommended. Basic experience with at least one statistical or econometric package will help participants gain the most from the practical sessions. The required programming depth depends on the selected software and course version.
5. 5. Will participants build their own econometric models?
Yes. Participants work through model specification, estimation, diagnostic testing, forecast evaluation and interpretation using practical datasets. The capstone requires participants to complete an applied econometric analysis relevant to central bank research.
6. 6. How does the workshop incorporate AI?
The programme examines machine learning and emerging AI forecasting methods as complements to established econometric models. Participants learn to compare predictive performance, identify data leakage, assess model limitations and preserve reproducibility and human oversight.
7. 7. What are the expected outcomes?
Participants will be able to select and estimate appropriate time-series models, assess their validity, produce and evaluate forecasts, analyse dynamic responses to economic shocks and communicate empirical findings for monetary policy and financial stability decisions.
Schedule & fees
| Dates | Location | Duration | Fee (USD) |
|---|
| 07/06/2027 - 18/06/2027 |
Kigali,Rwanda |
10 Days |
$3,500 |
| 13/09/2027 - 24/09/2027 |
Nairobi,kenya or Virtual |
10 Days |
$3,000 |
| 18/10/2027 - 29/10/2027 |
Lagos,Nigeria |
10 Days |
$3,500 |
| 25/10/2027 - 05/11/2027 |
Accra,Ghana |
10 Days |
$3,500 |
| 08/11/2027 - 19/11/2027 |
Zanzibar,Tanzania |
10 Days |
$3,500 |