Health and socio-economic status are the most critical elements when researching a community or state. One way to look at social aspects that influence a country’s development is to look at its exports, health, imports, income, inflation, life expectancy, total fertility, and GDP per capita. Cluster analysis and other machine learning (ML) forms are crucial for extracting useful information from the Socio-economic dataset, as is the evaluation of dimensional reductions and rakings. The dataset was collected via Rohan Kukkula’s Kaggle uploads, which included (16710) entries for many nations and their socio-economic variables. We use cluster and statistical analysis to find the nations needing the most aid to improve their economic and social situations. The characteristics in the dataset are reduced in dimensionality via principal component analysis. Two clustering methods, hierarchical and K-Means, were used. The results are the same when using both methods; however, K-means plots are easier to see than those using Hierarchical clustering. Using the clustering process, we categorise the nations according to their socio-economic status and health indicators. Policymakers, NGOs, and international development agencies might utilise the results of this study to help severely underdeveloped nations