Recommendation of who-to-follow and what-to-buy

• Main Author: Prasetya, Steve Alexander
• Other Authors: Zhang Jie
• Format: Final Year Project
• Language: English
• Published: 2018
• Subjects: DRNTU::Engineering::Computer science and engineering
• Online Access: http://hdl.handle.net/10356/75786
• Institution: Nanyang Technological University

The advancement of technology occurs so fast that it is often difficult to keep up with. This phenomenon affects a lot of things, and one of them is the e-commerce industry. With the rapidly growing user base of the industry, the amount of information also increases significantly. Fortunately, technology advances allow the industry to be on par in terms of data processing. The increasing popularity of online shopping has posed several problems for both buyers and sellers alike. Sometimes it is not quite straightforward to determine which items to display on the main page specific to each individual user. Should this happen, there would be an increased probability for the user to purchase items that are in tandem with his preferences. One such method to address this is called Collaborative Filtering, which is something used by Recommender Systems. It works by utilizing several other users’ preferences and matching it to one specific user to predict his. This project looks on a recommender system that is the Librec library and implements a user interface such that it is easier for developers in the e-commerce industry to analyze results and select which algorithms are worth using in the business. This is done by creating a Java application using a set of graphics and media packages called JavaFX.