Genre classification holds great significance for analyzing the flavor of attribute in one or more predetermined categories. Genre classification involves instances that can be categorized features based on emotion, adding complexity to the classification process. Music classification is used in Spotify, Deezer, Apple music incorporating stream prediction and recommendation system. The paper mainly helps to unfold the convergence of machine learning, genre classification, and basic genre recommendation multimedia analysis within the context of the Spotify dataset. This paper focuses on the application of data exploration, ML and data classification techniques to unravel patterns and insights within the Spotify dataset. Leveraging the rich and diverse data provided by Spotify, encompassing user interactions, audio features, and textual information, the study aims to develop robust classification models for music-related tasks. The paper explores various feature based classification to analyze what features are making it most popular to discern intricate patterns in the data and enhance the accuracy of genre classification. Spotify dataset includes features like explicit, liveness, valence to make it to what features makes it more engaging. In addition to genre classification, the project also endeavors to predict Artist Highlights, Popularity, Regional Variations. The anticipated outcomes include the development of accurate genre classification models. Recommendation based on genre and artist will be generated using euclidean similarity.