Implementation of recommender system on an E-commerce application

• Main Author: Mak, Jackson Jia Ming
• Other Authors: Zhang Jie
• Format: Final Year Project
• Language: English
• Published: 2017
• Subjects: DRNTU::Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
• Online Access: http://hdl.handle.net/10356/70298
• Institution: Nanyang Technological University

In the current day and age, technologies capable of processing millions of data within seconds had lead the world into an era where information is transforming the world. This also applies in E-commerce, it is almost impossible to find an E-commerce business that allows the customer to explore through its wide range of goods and services unaided. Filtering information has thus become an important part of the daily life. And Collaborative Filtering is the approach of filtering information in E-commerce. These, also known as Recommender Systems, aim to predict users’ ‘rating’ and ‘preference’ of their interests, have been widely utilize and are still continuing to grow. The report reviews on several Collaborative Filtering approaches and attempts to decide on the appropriate algorithms to use from a Java-based Recommender System, LibRec, on an E-commerce application that will be developed in the course of this project. As such, this E-commerce application, operating as a mobile application and on the web, will be able to implement the Recommender System to make recommendations. The implementation of the E-commerce backend is developed using Django Oscar that runs on Python as a programming language defers from the frontend mobile application where a mobile development framework Ionic is used, a completely different programming approach. Despite, Ionic is chosen due to its ability to run on multiple mobile platform, based on Cordova and AngularJS instead of a native mobile language, which allows extensibility and portability.