Speaker
Description
The IMF is modernizing how statistical data and metadata are produced and managed to support both AI-enabled access and enterprise data governance. This work is built around two closely related use cases. First, a standardized metadata model mapped to Dublin Core, DCAT, and SDMX Global Data Structure Definitions (DSDs) is used to generate consistent semantic descriptions for the IMF’s SDMX APIs and integrated search. This enables AI agents and users to discover and interpret datasets, indicators, dimensions, sources, and usage conditions directly from metadata rather than from scattered documents or hard-coded rules. Second, the IMF is developing a knowledge-graph-based Data Catalog as the Fund’s authoritative institutional registry for governed data assets, capturing lineage, approvals, lifecycle states, and access controls as structured, interlinked objects. This allows AI agents to understand not only what a dataset contains, but also its provenance, approval status, lifecycle position, and release conditions. The presentation shows how a standards-based architecture—combining GSBPM-based lifecycle management, SDMX artefacts, metadata standards, integrated search, and knowledge-graph-based governance—can provide a trusted discovery layer for data while strengthening enterprise data governance.