In order to generate precise behavioural patterns or user segmentation, organisations often struggle with pulling information from data and choosing suitable Machine Learning (ML) techniques. Furthermore, many marketing teams are unfamiliar with data-driven classification methods. The goal of this research is to provide a framework that outlines the Unsupervised Machine Learning (UML) methods for User-Profiling (UP) based on essential data attributes. A thorough literature study was undertaken on the most popular UML techniques and their dataset attributes needs. For UP, a structure is developed that outlines several UML techniques. In terms of data size and dimensions, it offers two-stage clustering algorithms for category, quantitative, and mixed types of datasets. The clusters are determined in the first step using a multilevel or model-based classification method. Cluster refining is done in the second step using a non-hierarchical clustering technique. Academics and professionals may use the framework to figure out which UML techniques are best for creating strong profiles or data-driven user segmentation.