Real-time context-aware recommender systems

Proposed Research: Existing recommender systems, even though very effective (like Amazon,
Netflix, Youtube etc) do not take into consideration any contextual information, such as time and
place. In recent times, context-aware recommender systems have attracted a lot of research and
industrial attention. In this project, we aim to address the unsolved challenges that comes with
incorporating contextual information in recommender systems.
Benefit to Namkis: Namkis enables users to review places and businesses around them, in terms of
smiles and scowls. Based on these reviews, relevant businesses are recommended to the users.
Improving the algorithms and inventing new techniques will aide namkis to provide better
recommendations to its users. This will result in higher engagement & greater virality of product.
Mitacs

Faculty Supervisor:

Laks Lakshmanan

Student:

Partner:

Discipline:

Computer science

Sector:

Professional, scientific and technical services

University:

The University of British Columbia

Program:

Accelerate