Taxonomic Delineation of Musical Genres Through Computational Paradigms: An Exploration Employing the K-Nearest Neighbors (KNN) Algorithm

The conventional challenge in the realm of music categorization pertains to prognosticating the appropriate genre of music that aligns with a given tradition or set of conventions. With assets totaling $26 billion, a music platform commands a substantial market share and presently dominates the majority of the music streaming industry. Boasting an extensive database housing thousands of songs, this platform asserts its capability to offer impeccable musical selections tailored to each user. Much akin to industry frontrunners like Wynk, Amazon Music, and Spotify, significant investments have been made in sophisticated analytics to enhance how consumers discover and engage with music. These analytical endeavors heavily lean on Artificial Intelligence (AI), leveraging methodologies such as deep learning, collaborative filtering, Natural Language Processing (NLP), and others. Advanced song attributes such as danceability, energy, acoustics, rhythm, and dynamics are scrutinized. The ultimate aim of this analytical process is to tackle the perennial question of musical compatibility, often pondered during initial romantic encounters. Modern enterprises harness music classification to furnish personalized recommendations to consumers, as evidenced by platforms like Soundcloud and Spotify, or as standalone services exemplified by Shazam. A pivotal step in achieving these objectives is the identification of music genres. The utilization of AI techniques in music analysis has proven particularly efficacious in discerning patterns and models from vast datasets. Despite the relatively recent integration of AI methods, particularly in deep learning, machine learning techniques continue to predominantly drive the classification of musical genres. This paper introduces an extensive music dataset encompassing a diverse array of genres including Rock, Pop, Folk, and Classical. The system employs a deep learning approach and trains and classifies utilizing the K-Nearest Neighbours (KNN) algorithm.