> For the complete documentation index, see [llms.txt](https://docs.alphageo.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.alphageo.ai/macro-suite/migration-modeler.md). # Global Migration Modeler (GMM) ## Introduction AlphaGeo's Global Migration Modeler (GMM) provides a comprehensive corridor-level view of population movements and forecasts international flows between origin and destination country pairs for distinct demographic groupings including (a) investors (b) professionals (c) students, and (d) tourists. The GMM gives decision makers corridor-level insights into population mobility trends, demographic pressures, labor market dynamics, demand for goods and services, and other consequences of shifting migration flows at a global scale. Explore Global Migration Modeler ## Gaps in Global Migration Data No single dataset captures bilateral migration at a global level. Most that exist have one or more of the following shortcomings: * Old and lagging data. Prominent data sources such as UN DESA capture bilateral flow pairs at erratic intervals and often represent estimates. * Failure to account for sudden reversals. Geopolitical and policy shifts have led to mass return movements (e.g. Syrians from Turkey, Afghans from Pakistan and Iran, US suspension of refugee admission) that defy linear historical trends. * Uneven coverage. Regional sources (such as Europe’s OECD and Eurostat) offer reliable and continuous data, but do not cover some of the largest corridors (such as the Gulf states, South Asia and Southeast Asia). Furthermore, some of these regions do not provide the composition of immigrants by nationality. * Conflicting definitions. Foreign-born, foreign-citizen, and registration-based counts differ materially for the same country (e.g., Japan counts 4.1M foreign residents versus 3.4M foreign-born). Merging these categories produces incoherent corridor totals and spurious year-over-year swings that reflect definitional artifacts rather than real movement. ## AlphaGeo’s Approach ### Estimating flows We begin by constructing a migration stock baseline from international and government sources, upon which we layer estimated flows from a range of sources (both official and unofficial such as media and monitoring groups). Note that changes in stock reveals net movement, not gross flow, with the residual accounted for by migrant mortality, naturalization and reclassification. Where gross churn matters — notably the high-turnover Gulf labor corridors — we supplement our dataset with visa issuance and work-permit data rather than relying on stock deltas alone. ### Data refresh Our dataset incorporates timely overlays of new information from the latest national figures and other sources to update our historical baselines for each country. ### Reconciling sources Given discrepancies in the definition of various migrant categories, we transparently tag each datapoint with a source, date, confidence tier, and annotation explaining the figure, allowing users to filter and weight corridors by data quality. ## Modeling Migrant Flows AlphaGeo’s generative AI pipeline converts unstructured sources (e.g. government policies, media reports, industry publications, etc.) into structured corridor-level +/- modifiers to projected future flows, each with a confidence tier. Each destination country also has a dynamic weight associated with its attractiveness to the four major demographic groups – investors, professionals, students, tourists – based on AlphaGeo’s proprietary migration competitiveness framework. We combine the harmonized series of corridor indicators with the country-level migration competitiveness scores to forecast near-term origin-destination migration flows for all country pairs calibrated to each demographic segment. Clients may provide supplemental data or request modifications to country-level weights to customize the projected migration forecasts. ## Sources * UN DESA — International Migrant Stock (bilateral stock baselines) * OECD — International Migration Database * Eurostat — EU migration statistics and residence permits * UNHCR — refugee, asylum, and returnee data * IOM — Displacement Tracking Matrix and flow monitoring * GLMM — Gulf Labor Markets and Migration program * Frontex — Irregular border-crossing detections * ILO — international labor migration statistics * UNESCO Institute for Statistics * National statistical agencies, census bureaus, and immigration authorities * National visa issuance and work permit registries --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.alphageo.ai/macro-suite/migration-modeler.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.