World Journal of Engineering Research and Technology

Hruthik G. R., *Yashas M. D., Jhenkar, Kiran Kumar N., Sindhu K. S. (Asst. Professor), Shruthi B. S. (Asst. Professor)

ABSTRACT

The study aims to develop an innovative music recommendation system to address specific concerns. It employs K Nearest Neighbour Classification and Random Forest Classifier algorithms. This novel approach utilizes Spotify API calls, implementing various machine learning algorithms such as K Nearest Neighbour Classification, Decision Tree Classifier, and Random Forest Classifier. The system recommends music to users based on genre, year range, and music features like acousticness, danceability, energy, tempo, and valence.The prevalence of digital music and mobile-accessible commercial music streaming services has made music more accessible. However, organizing vast digital music libraries can be time-consuming and lead to information overload. Therefore, a music recommender system that can automatically analyse music libraries and suggest suitable songs to consumers is highly beneficial. Such a system allows music providers to predict and offer relevant songs based on users' past music preferences, increasing user satisfaction and diversity in music consumption. The significance of a music recommendation system for music distributors cannot be overstated. It predicts songs that consumers would enjoy and promotes them, leading to increased user satisfaction and a wider music selection.

[Full Text Article] [Download Certificate]