User Modeling for Course Recommendation Systems - BC-407

Preferred Disciplines: Machine Learning, Data Science (Masters or PhD)
Project length: 4 months (1 unit)
Approx. start date: As soon as possible
Location: Vancouver, BC
No. of Positions: 2
Preferences: None
Company: HackHub

About Company:

HackHub is a talent incubation platform. By working with industry experts, companies, educational institutions and incubators, HackHub helps to reinforce both talents’ and companies’ professional growth through education programs and hackathon events.

Summary of Project:

A content-based personalized recommendation system learns user specific profiles from user actions so that it can deliver course content tailored to each individual user’s interest. Currently, we are using a robust weight system which generated by the content views and user inputs with tags. By getting this recommendation system more stable and accurate, we would like to leverage machine learning to determine user interests and classify users by their actions on our platform such as file uploads, video plays, and discussion keywords.

Research Objectives/Sub-Objectives:

  • Increase accuracy for existing recommendation system
  • Build machine learning model from existing data

Methodology:

    • Use Python oriented machine learning framework such as TensorFlow to build the model
    • Use natural language processing methods to analyze existing user data

    Expertise and Skills Needed:

    • Python
    • TensorFlow
    • NLP

    For more info or to apply to this applied research position, please

    1. Check your eligibility and find more information about open projects.
    2. Interested students need to get the approval from their supervisor and send their CV along with a link to their supervisor’s university webpage by applying through the webform.
    Program: