Deep Collaborative Filtering using two stage information Retrieval

The company wants to develop a state of art recommendation system for the clients. A recommendation system is a piece of software that provides products’ suggestions to customers on a website. For example the products suggestions that can be seen on Amazon’s web page are generated by its recommendation engine.
The typical recommendation engines work by utilizing the existing user-product preferences information. They recommend products to a user by comparing his preferences to other similar users’ preferences. The typical example of this is Users who bought item-A also bought item-B. This suffers from the problem of cold-start. This happens say when a user logins for the first time and has no preference information.
We propose to solve this problem by using user-content information and using a technique called deep learning. TO BE CONT’D

Faculty Supervisor:

Richard Zemel

Student:

Partner:

Layer 6 AI

Discipline:

Computer science

Sector:

Information and Communications Technology; Technology; Commercial Services

University:

University of Toronto

Program: