A MACHINE LEARNING APPROACH TO CATEGORIZING COUNTRIES BY SOCIO-ECONOMIC AND HEALTH DEVELOPMENT FACTORS USING PCA, K-MEANS, AND SILHOUETTE SCORING
- Version
- Download 2
- File Size 477.05 KB
- File Count 1
- Create Date 7 June 2025
- Last Updated 7 June 2025
A MACHINE LEARNING APPROACH TO CATEGORIZING COUNTRIES BY SOCIO-ECONOMIC AND HEALTH DEVELOPMENT FACTORS USING PCA, K-MEANS, AND SILHOUETTE SCORING
Authors:
Dr. T. AMALRAJ VICTOIRE1,M.VASUKI2, S.ANITHA3
1 Professor, Department of MCA, Sri Manakula Vinayagar Engineering College, Puducherry-605107, India.
2 Associate Professor, Department of MCA, Sri Manakula Vinayagar Engineering College, Puducherry-605107, India.
3PG Student, Department of MCA, Sri Manakula Vinayagar Engineering College, Puducherry-605107 India.
amalrajvictoire@gmail.com1, dheshna@gmail.com2, anithasenthil58@gmail.com3
Abstract: This project uses unsupervised learning techniques to categorize countries based on socio-economic and health factors, helping HELP International, a humanitarian NGO, allocate $10 million in aid more effective helping HELP International give aid more effectively. Income, infant mortality, how good health care is, and life duration are all measured to see how developed a country is using clustering and principal component analysis. Using data helps the NGO discover which regions need the most help. By learning what is needed, HELP International can focus their effort on the most vulnerable people first. By using unsupervised learning, the project categorizes countries depending on their health and social standards, which allows HELP International to direct their $10 million worth of aid to regions that need it most. The project groups countries in terms of their development using K-means and PCA, while examining factors such as income earned, child deaths, healthcare systems, and an average person’s expected lifespan. By taking this action, the NGO can easily tell which communities are the most in need of outside assistance. The information received guides HELP International in distributing resources to the people who most need it. This project demonstrates that machine learning can help support humanitarian activities, improve decisions, and increase how effective aid is, bettering the lives of people in unprivileged regions.
Keywords: Unsupervised Learning, K-means Clustering, PCA, Socio-Economic Analysis, Health Indicators, Humanitarian Aid, Data-Driven Decision Making, Country Clustering, Poverty Alleviation, HELP International.
Download