Clustering aims to discover meaningful groupings in data. There are a variety of clustering techniques that can be used such as Gaussian mixtures and K-Means methods depending on the data analysis requirements. Clustering has found application to the insurance domain to analyze insurance data. The goal of this thesis is to provide an analysis of insurance data from public datasets in collaboration with the Adacta company, explaining the underlying process, descriptive attributes, and groupings. One main task will be to get familiar with different clustering approaches that are currently being used for insurance purposes. Then, to analyze and review clustering techniques for numerical and mixed data types. Afterward, use the learned clustering techniques to analyze the provided insurance data by using common data science tools to compare and visualize clustering results.