| Summary: | The constant advancement of web development trends and technology has resulted in a big number of web systems that are frequently visited on a regular basis. Among the web systems that have been established, there are systems that allow users to listen to music online without having to download it to their devices. With the increasing popularity of music streaming, music recommender systems are important instruments for increasing digital music consumption. Machine Learning is a form of Artificial Intelligence that will make systems to think like human being. Machine Learning allows a system to learn gradually to improve its accuracy in predicting future outcome. The objective of this project is to develop a music recommendation system using one of the Machine Learning techniques which is content-based filtering technique. The aim of this study is to study about music recommender system on how it is implemented and to design and develop a music recommender system. In this study, methods of K-Mean Clustering, Euclidean Distance and Cosine Similarity are implemented. These are the popular algorithm for unsupervised learning, a machine learning method to analyse and cluster datasets. These algorithms identify hidden patterns or data groupings without the assistance of a human. It is the best option for exploratory data analysis because of its ability to find informational similarities and differences. Based on analysis on music user listen to during usage, the system will determine the feature values of that song. This allows the algorithm to select similar songs after calculation in database would best match the user's interests at any given time. K-Mean Clustering will cluster the data, according to the similarities of each song, separate them by different group. Cosine Similarity will calculate the cosine distance with other data and recommend the one with shorter distance. Euclidean Distance will calculate the direct distance between two vectors and recommend the one with shorter distance.
|
|---|