Internship_project_ppt - Rahul-1.pptx engineering course

H

1. Internship Project Presentation on “Music Recommendation System” Student : Rahul V Patil USN : 1RN20CS109 Guide : Supritha N Designation : Asst. Professor Department of Computer Science and Engineering RNS Institute of Technology 2023-24

2. CONTENTS INTRODUCTION OBJECTIVES PROBLEM STATEMENT METHODOLOGY RESULTS AND DEMONSTRATION CONCLUSION Dept. of CSE,RNSIT 2023 - 24 2

3. INTRODUCTION One of the most used machine learning algorithms is recommendation systems. A   recommender  (or recommendation)  system  (or engine) is a filtering system which aim is to predict a rating or preference. Which type of recommender can we have? There are two main types of recommender systems:  1.Content-based filters 2.Collaborative filters Collaborative recommendation system is used in this project. KNN algorithm and Clustering techniques are deployed in this System.

4. OBJECTIVES The objectives of establishing a Music Recommendation System Model are as follows: Content Diversity : Facilitate a diverse range of content inclusion because not everyone likes the music of a particular genre. User Study : Studying and predicting if a user will benefit from a particular result. Use of various functions : Use of various functions to provide effective, efficient accurate results.

5. PROBLEM STATEMENT Recommendation systems have emerged as a result of the large amount of data available on the Internet. Many firms, such as W ynk music and ganna.com for music streaming, are now employing recommender systems to their advantage. We provide a framework in this particular situation that can then recommend new melodies to clients based on their preferences. This initiative primarily focuses on providing music recommendations to music fans in order to assist them in listening to tracks that they may enjoy.

6. METHODOLOGY The development of a music recommendation system uses the previous record of user music playlist and algorithms such as KNN and matrix factorization. Project Planning: Define the dataset, algorithms and goal of the Project. Test and train the dataset imbibing the algorithm. Plan the structure and visualize the data and execute the algorithm on the data. User: Analyze the user’s music playlist and previous genres of music on the platform. Count the songs listened to by the user and gain the average. Use the model and recommendations.

7. RESULTS AND DEMONSTRATION Bar Graph Visualization of User Playlist

8. CONCLUSION In conclusion, the Music Recommendation System stands as a testament to the effectiveness of the Machine Learning Model which is a Supervised Learning method using the K-Nearest Neighbor Algorithm and Clustering as well as Matrix Factorization techniques to build a perfectly capable AI model that can work on its own further on various data and recommend random intriguing music to the user. This method is already used on various Music platforms and will find its application in many more years to come.