High-Frequency Data Analytics for Inflation, GDP and Economic Activity Monitoring Training Workshop

Course overview

This specialised workshop equips central bank economists, statistical analysts, monetary policy researchers and economic intelligence teams with the skills to monitor economic conditions using high-frequency and alternative data sources. It focuses on improving the timeliness of inflation assessment, GDP nowcasting and economic activity monitoring between official statistical releases.

Participants learn how to combine conventional macroeconomic indicators with daily, weekly and monthly data such as mobile payments, electronic transactions, fuel prices, electricity consumption, transport activity, customs records, online prices and business sentiment. Statistical methods, machine learning and AI-assisted analytics are applied to identify emerging trends, estimate current economic conditions and detect turning points.

Course objectives

• Identify and integrate high-frequency indicators from official statistics, financial transactions, commodity prices, electronic payments, transport, energy and business surveys for real-time economic monitoring.
• Strengthen evidence-based monetary policy analysis by validating alternative indicators, measuring forecast performance, managing data-quality risks and translating timely economic signals into policy-relevant insights.
• Build automated economic monitoring dashboards that track economic activity, identify turning points, assess data revisions and communicate changes in macroeconomic conditions.
• Apply AI and advanced analytics to inflation monitoring by tracking price movements, detecting emerging inflation pressures and evaluating changes in food, fuel, transport and other consumer prices.
• Develop GDP nowcasting models that combine monthly, weekly and daily indicators to estimate current-quarter economic growth before official national accounts data are published.

Who should attend

Course content

• Module 1: Foundations of High-Frequency Economic Monitoring The role of real-time economic intelligence in central bank decision-making, differences between high-frequency monitoring, forecasting and nowcasting, data frequency and publication lags, leadi
• Module 2: High-Frequency Data Sources for Economic Analysis Working with daily, weekly and monthly indicators from national statistics offices, tax authorities, customs agencies, electronic payment systems, mobile money platforms, financial markets, util
• Module 3: Macroeconomic Data Engineering and Preparation Building reliable data pipelines, collecting and consolidating economic time series, handling missing observations and outliers, aligning different reporting frequencies, adjusting for seasonality
• Module 4: High-Frequency Inflation Monitoring and Price Analytics Tracking daily and weekly prices for food, fuel, transport, housing-related goods and other consumer products; measuring price changes and dispersion; monitoring regional price differences
• Module 5: GDP Nowcasting and Economic Growth Estimation Estimating current-quarter GDP growth before official publication using monthly economic indicators, dynamic factor models, mixed-frequency regressions, bridge equations and machine-learning methods
• Module 6: Monitoring Consumption, Payments and Domestic Demand Analysing mobile money transactions, electronic payments, card spending, retail activity, imports of consumer goods and business turnover indicators to assess consumption patterns and domesti
• Module 7: Industrial Production, Agriculture and Sectoral Activity Using electricity consumption, manufacturing output, industrial production, fuel sales, freight movements, agricultural market arrivals, rainfall, crop conditions, tourism activity and co
• Module 8: Labour Markets, Business Surveys and Economic Sentiment Interpreting employment indicators, job advertisements, payroll information where available, business confidence surveys, purchasing managers’ indices, consumer expectations and firm-lev
• Module 9: Time-Series Analytics and Leading Economic Indicators Applying growth rates, rolling averages, seasonal adjustment, cross-correlations, lag analysis, trend decomposition and anomaly detection. Evaluating leading, coincident and lagging indicato
• Module 10: AI and Machine Learning for Real-Time Economic Monitoring Applying regression, random forests, gradient boosting, regularisation and other suitable machine-learning methods to high-dimensional economic datasets. Selecting relevant predictors,
• Module 11: Mixed-Frequency Econometric Models and Dynamic Factor Analysis Using mixed-data sampling (MIDAS) regressions, bridge models, dynamic factor models and state-space approaches to combine indicators published at different frequencies. Understandi
• Module 12: Satellite, Geospatial and Alternative Data for Economic Activity Exploring satellite-derived night-time lights, geospatial measures of urban expansion, road activity, shipping movements, agricultural vegetation indicators and other alternative
• Module 13: Automated Economic Dashboards and Real-Time Intelligence Systems Designing interactive dashboards using Power BI, Excel or Python-based visualisation tools; tracking inflation, GDP nowcasts, industrial activity, consumption, exchange rates, cr
• Module 14: Data Governance, Model Validation and Statistical Quality Assurance Managing data confidentiality, privacy, licensing, representativeness and responsible use of transaction-level data; validating alternative indicators against official statist
• Module 15: Integrated Central Bank Economic Monitoring Capstone Developing an integrated real-time economic monitoring system using a practical dataset. Participants combine price indicators, economic activity data and official macroeconomic statistics;
• Module 14: Data Governance, Model Validation and Statistical Quality Assurance Managing data confidentiality, privacy, licensing, representativeness and responsible use of transaction-level data; validating alternative indicators against official statist
• Module 15: Integrated Central Bank Economic Monitoring Capstone Developing an integrated real-time economic monitoring system using a practical dataset. Participants combine price indicators, economic activity data and official macroeconomic statistics;

General notes

• Practical Exercises and Case Studies Daily and weekly food price monitoring, development of a supplementary high-frequency inflation indicator, comparison of observed prices with official CPI inflation, GDP nowcasting using monthly economic indicators, integration of electronic payment data into domestic demand analysis, monitoring industrial production through electricity consumption, analysis of fuel prices and transport costs as inflation signals, assessment of agricultural output and weather-related economic shocks, development of a business sentiment indicator, detection of unusual economic activity using machine learning, comparison of dynamic factor and machine-learning nowcasts, analysis of data-release surprises and GDP nowcast revisions, monitoring economic turning points through a composite activity index, creation of an automated economic monitoring dashboard, and preparation of a monetary policy briefing based on real-time economic evidence.
• Recommended Tools and Technology Stack Data preparation and analysis: Microsoft Excel, Python, pandas, NumPy and SQL. Econometric analysis: EViews, Stata, R, statsmodels and suitable mixed-frequency modelling libraries. Machine learning: scikit-learn, XGBoost and appropriate time-series forecasting libraries. Visualisation and reporting: Power BI, Excel dashboards, Jupyter notebooks and Python visualisation libraries. Alternative data analysis: Geospatial tools, satellite-derived datasets, electronic payment aggregates, business surveys and authorised market-price datasets. Recommended analytical methods: Dynamic factor models, MIDAS, bridge equations, state-space models, ARIMA, regression, machine learning, seasonal adjustment, anomaly detection, nowcasting and forecast evaluation. The specific tools can be adapted to the institution’s existing platforms, available datasets, licensing arrangements and technical capabilities.
• Practical Outputs and Deliverables High-frequency economic data inventory and source assessment matrix. Economic data-quality and preprocessing checklist. High-frequency food and fuel price monitoring dataset. Supplementary inflation monitoring model. GDP nowcasting model using monthly economic indicators. Mixed-frequency data integration framework. Domestic demand and electronic payments analysis template. Composite economic activity indicator. AI-based economic anomaly detection model. Model performance and forecast evaluation scorecard. Automated economic monitoring dashboard. Economic data-release calendar and nowcast revision tracker. High-frequency economic monitoring methodology document. Monetary policy intelligence report summarising current economic signals, risks and uncertainties.
• : Develop practical skills in high-frequency data analytics, GDP nowcasting, inflation monitoring, AI-powered economic indicators and real-time economic intelligence for central banks and policy institutions.
• Research references The course is supported by established research and practical central bank applications: - IMF — Nowcasting GDP Growth for Kenya (2026). A particularly relevant example of combining conventional monthly indicators with digital transaction data to estimate quarterly GDP growth. International Monetary Fund +1 - IMF — Real-Time Economic Indicators Help Better Track Activity in Africa. Discusses machine learning and high-frequency indicators for economic monitoring in African economies. International Monetary Fund - BIS — Artificial Intelligence and the Economy: Implications for Central Banks. Explains the role of timely, high-dimensional data and AI-supported nowcasting in central bank analysis. Bank for International Settlements - IMF — Nowcasting Economic Growth with Machine Learning and Satellite Data (2026). Examines the use of satellite-derived night-time lights and machine learning to improve GDP estimates.

Frequently asked questions

Schedule & fees