Big Data for Macroeconomic Statistics (BDMS) — Training Program
Source details
- Canonical URL
- Big Data for Macroeconomic Statistics (BDMS) — Training Program
Other formats
Bibliographic details
- Session: PT 26.03
- Location: Asuncion, Paraguay
- Dates: May 4-8, 2026 (1 week)
- Delivery method: In-person Training
- Primary language: English
- Interpretation language: Spanish
Overview
- Event: Big Data for Macroeconomic Statistics (BDMS), Session No.: PT 26.03.
- Location: Asuncion, Paraguay.
- Date: May 4-8, 2026 (1 week).
- Delivery Method: In-person Training.
- Primary Language: English.
- Interpretation Language: Spanish.
Target Audience & Qualifications
- Intended participants: technical staff and managers from national statistics offices (NSOs) and central banks involved in macroeconomic statistics, nowcasting, and data science projects.
- Suitable roles: economists, statisticians, data scientists, and decision-makers overseeing related projects or teams.
Course Description & Delivery
- Organizer/instructor: data scientists of the IMF Big Data Center.
- Format: lectures and hands-on workshops.
- Emphasis: applications of Big Data and advanced technologies to generate high-frequency and detailed statistics to enhance macroeconomic monitoring and research in the region.
- Participant engagement: opportunities to present and discuss use cases, engage in discussions, and benefit from shared insights and experiences.
Course Objectives
- Provide support in setting up Big Data architecture, encompassing data extraction, preprocessing, and visualization in participants' organizations.
- Demonstrate practical knowledge of machine learning modeling, variable selection, performance analysis, and model selection for GDP nowcasting and trade monitoring (based on the IMF's "PortWatch" platform).
- Demonstrate practical skills in the use of Google Earth Engine (GEE), Dynamic World, Jupyter Notebook and other geospatial and data science packages to analyze satellite data and generate high-frequency macroeconomic statistics.
- Carry out textual analysis with natural language processing (NLP) technologies to support macroeconomic analysis.
- Demonstrate the application of these Big Data technologies and resources to improve timelines and granularity of official statistics.
- Facilitate peer-learning on Big Data applications and explore collaborations between agencies working on projects of mutual interest.
- Gain insights into setting up effective data science teams and developing institutional Big Data strategies to support innovation for macroeconomic statistics.
Skills, Tools, and Thematic Coverage
- Machine learning for GDP nowcasting and trade monitoring, including variable selection, performance analysis, and model selection.
- Geospatial analysis using Google Earth Engine (GEE), Dynamic World, and related packages.
- Jupyter Notebook-based hands-on workflows for data preprocessing, analysis, and visualization.
- Natural language processing (NLP) techniques for textual analysis to inform macroeconomic indicators.
- Big Data architecture components: data extraction, preprocessing, visualization, and institutional strategy for data science teams.
Logistics & Funding
- Travel, accommodation, and per diem costs: to be arranged and funded by participants' sponsoring agencies.
References