About This Project
Making the Invisible Visible
15,000+ Lao Minnesotans are invisible in state data systems because they are aggregated under “Asian” or “Other” categories. This portal disaggregates the data, reveals hidden disparities, and shifts community support from reactive crisis response to predictive early intervention.
The Problem
When data about Lao Minnesotans is aggregated under “Asian,” critical disparities vanish. The aggregated “Asian” category — which includes Chinese, Japanese, Korean, Indian, and other communities with vastly different socioeconomic profiles — masks the unique challenges faced by Southeast Asian refugee communities.
Hidden by Aggregation
24%
Gambling addiction rate
4.8x the national average of 5%
34.8%
Linguistic isolation rate
Classified “High Risk”
45.3%
Elders with no formal schooling
Invisible in “Asian” averages
The Solution
Disaggregated Data Infrastructure
A comprehensive database of Lao-specific indicators across health, economic, education, and housing domains — showing what aggregated data hides.
AI-Powered Narrative Analysis
Multilingual NLP engine analyzing community narratives in Lao and English, extracting themes, sentiment, and early warning signals from community voices.
Predictive Risk Models
ML models predicting risk for gambling addiction, educational dropout, mental health crises, and elder isolation — enabling preventive intervention.
Community-Governed Ethics
Community IRB oversight, differential privacy, algorithmic fairness auditing, and consent management — data sovereignty by the community, for the community.
Project Lead
Dr. Phouthakannha Nantharath
Research Scientist, Minnesota Department of Revenue
DBA in Business Economics | 20+ Peer-Reviewed Publications
Core Faculty, Khon Kaen University (Thailand)
15 Years of Lao Community Leadership in Minnesota
2026 Bush Fellow
“Behind every statistic is a family, a story, a life that deserves to be counted accurately and served with precision.”