I am a final year Creative Computing student. Throughout my 4 years in iadt, I have developed knowledge and skills in a wide range of technologies, problem solving and team work.
A recommender system is a system that uses historical data to predict user preferences by using machine learning. This paper outlines the design and development of one of these systems with the intention of providing a method of learning about machine learning, algorithms and recommender system methods. MusicRec uses historical listening data from Last.fm users to provide recommendations for artists. This is achieved using item-based collaborative filtering which calculates the similarity of items based on how users have rated those items. This project is multi-disiplinary, incorporating data science with conventional programming and design. The recommender uses Python, SciKit-Learn, NumPy and Pandas.
The aim of conducting this research and developing this project is to gain a deeper understanding of how recommender systems implement machine learning to perform their function.
The main goal of this project was to develop a recommender system. The intended purpose of the application was to provide users with music recommendations. the main goals in terms of the learning outcome were achieved, I now have a much deeper understanding and grasp on machine learning, artificial intelligence and recommender systems.