From June 16–18 in Malmö, the 4th International Forum on Migration Statistics (IFMS 2025) brings together statisticians, policymakers, demographers, and data scientists to advance innovative tools—especially Big Data and AI—for richer, more timely migration statistics.
One particularly promising innovation, already used by the UN International Organization for Migration (IOM) as part of its Diaspora Mapping and Engagement Toolkit, is personal name classification, a technique that leverages large datasets of names to infer migration patterns and origins. Here’s how this method can revolutionize migration statistics:
1. Mapping Real-Time Flows
Traditional national censuses and administrative records can be outdated or inconsistent across countries. By mining large-scale digital traces—like publication records, social media, or public registries—personal names can indicate likely migrant origin, enabling near real-time tracking of migration flows .
2. Disaggregated and Granular Data
Name-based models can classify individuals at fine levels (e.g., country or sub-national origins). Namsor classification tool offers several taxonomies, at the country level or even at the sub-country level (in the case of India, at the state level). For instance, an approach applied to over 8 million scholars achieved up to 84 % F1 accuracy for broad nationality and 67 % at country level arxiv.org. This granularity helps fill gaps in origin-destination matrices, key to IFMS’s goals on disaggregated, accurate stats.
3. Detecting Return Migration & Dual Flows
Name-classification helps distinguish between first-generation migrants and returnees. In scholarly data, nearly half of those emigration-designated scholars were return migrants once their name-origin was considered, revealing previously hidden reverse flows.
4. Boosting Timeliness & Forecasting
Coupled with AI, names can be triangulated with other Big Data sources—like Google Trends or mobile phone records—to forecast flows and migration events before official reporting. AI models with Big Data have cut forecast errors by up to 80% compared to traditional methods .
5. Enhancing Policy & Integration Pathways
IFMS 2025 emphasizes using migration data to support socioeconomic integration and informed policy-making. Name-based insights help pinpoint underrepresented migrant communities, tailor integration services, and direct resources more effectively.
6. Gender Intersectionality: Uncovering Hidden Inequities
Gender plays a critical role in shaping the migrant experience—but often goes underrepresented in conventional data systems. By incorporating gendered name classification into Big Data mining:
- Gender-specific patterns in migration (e.g., feminization of care work or male-dominated construction migration) can be identified.
- Intersectional inequalities—where gender, ethnicity, and migrant status intersect—become visible, especially in fields like employment, education, and health outcomes.
- Policy design improves, enabling gender-sensitive integration programs, visa policies, and labor protections.
In contexts where gender data is missing or unreliable, personal names can serve as a proxy indicator, helping address data gaps in line with IFMS 2025’s theme of inclusive, gender-responsive migration statistics. Namsor Gender classification is the AI model powering the European Commission SheFigures reporting.
🔍 Why Personal-Name Classification Matters at IFMS 2025
| Benefit | Impact |
|---|---|
| Timeliness | Real-time flow detection versus slow census updates |
| Depth | Fine-segment origin/destination insights |
| Accuracy | Reveals hidden patterns like return migration |
| Forecasting Power | Enables proactive policy responses |
| Integration Support | Facilitates targeted social and economic planning |
These align directly with the forum’s core themes: improving timeliness, accuracy, disaggregation, and using innovative data tools, including AI and Big Data
https://x.com/ElianCarsenat/status/1934529164725387597
Looking Ahead
Name-based classification is not a standalone panacea—it must be cross-validated with administrative records and privacy-conscious data practices. However, within IFMS’s vision, it represents a powerful tile in a mosaic of improved migration measurement.
As IFMS 2025 convenes in Malmö, this technique promises to enrich migration statistics with speed, scale, and depth—supporting data-driven, inclusive migration policies worldwide.
Image credits : picture taken today in Malmö by Elian Carsenat, with a District 9 insert made using OpenAI. District 9 (2009), directed by Neill Blomkamp, serves as a powerful allegory for migration, segregation, and ethnic conflict.
About NamSor
NamSor™ Applied Onomastics is a European vendor of sociolinguistics software (NamSor sorts names). NamSor mission is to help understand international flows of money, ideas and people. We proudly support Gender Gap Grader.