#UIDAI Data Hackathon 2026 Winners
 S.No. |
 Prize Category |
 Idea/Concept |
 Team ID, Lead and Member |
|---|---|---|---|
| 1 | First Prize Winner | Our approach analyzes India Aadhaar enrollment using 4.35 million records across 36 states 960 districts and 19700 pincodes. We developed a framework integrating 50 plus features through 14 external APIs including Open Meteo Census 2011 NITI Aayog SDG indices and RBI statistics. Our methodology combines statistical analysis ANOVA and Kruskal Wallis with machine learning 117 models Random Forest XGBoost LightGBM and Bayesian causal networks to uncover temporal geographic socioeconomic and climate patterns. Key findings reveal geographic inequality Gini 0.707 inverse HDI enrollment relationships indicating successful penetration in underserved regions weekend efficiency gains 33 percent higher and significant climate impacts. We achieve 99.97 percent classification accuracy R squared greater than 0.85 for demand forecasting and identify 20 priority underserved districts in UP and Bihar. Results provide actionable policy recommendations for optimizing coverage and resource allocation. | Id: UIDAI_549, Lead: Aheli Poddar, Member:Shuvam Banerji Seal, Alok Mishra |
| 2 | Second Prize Winner |
This project presents a data driven strategy to optimize UIDAI Aadhaar operations using 5.4 million enrolment and update records We introduce the Outreach Priority Index OPI to rank districts using coverage gaps youth concentration migration pressure and enrolment trends enabling targeted deployment of mobile units staffing update kiosks and biometric devices to reduce failures and improve service reliability
|
Id: UIDAI_10137 Lead: Sumit Kumar, Member: Ansh Patidar |
| 3 | Third Prize Winner |
Aadhaar Data Intelligence and Migration Patterns Analysis An analytical framework transforming UIDAI Aadhaar data into actionable policy insights KEY INNOVATIONS 1 MIGRATION INDEX for population mobility analysis 2 ANOMALY DETECTION using Z score analysis 3 DIGITAL DESERT MAPPING for underserved areas 4 DATA QUALITY FRAMEWORK for state name normalization METHODOLOGY Multi level analysis from State to District to Pincode Cross dataset correlation Time series and age pattern analysis 12 visualizations with reproducible Python code
|
Id: UIDAI_4136 Lead: Satyam |
| 4 | Fourth Prize Winner |
Child Biometric Gap Index – CBGI – A Data Driven Framework for Prioritizing District Level Interventions in Mandatory Biometric Updates
|
Id: UIDAI_1867 Lead: Madhav Dogra |
| 5 | Fifth Prize Winner |
Predictive Gap Analysis Engine for Mandatory Biometric Updates MBU Gap Analyzer is a predictive analytics system designed to identify children who have not completed their Mandatory Biometric Updates in the Aadhaar system Children must update their biometrics at ages 5 and 15 years If they miss these updates their Aadhaar becomes inactive blocking access to school admissions scholarships mid-day meals and Direct Benefit Transfers Our solution uses a 3-layer approach Cohort Tracking to calculate district-wise compliance gaps Service Desert Identification using K-Means clustering to find underserved areas and Demand Forecasting using LSTM deep learning to predict future MBU workloads This helps UIDAI proactively deploy resources to prevent children from losing government benefits
|
Id: UIDAI_1494, Lead: Piyush Verma, Member: Stiwart Stance Saxena |