Extracted the heart disease dataset from UCI Machine Learning repository to develop machine learning model unsupervised for identifying a possible heart disease at an early stage.

Performed exploratory data analysis using such as correlation coefficient among independent variables, outliers in the dataset, relation between categorical and continuous variables using ANOVA.

Normalized the dataset and performed principal component analysis to extract principal components which explained 50% of variability in the dataset.

Used different clustering methods to identify the patients having heart disease with an accuracy of 84%. Prepared R Shiny dashboard for visualization of clustering results using different metrics.