Enhanced Content-Based Similarity Detection for Book Recommendation

Recommendations is one of the main ways Kobo users discover content on the platform. By using purchase history, Kobo can suggest other books similar to a certain item. However, this does not provide meaningfulrecommendations in some cases, especially for bestsellers and fiction books. Currently, only for books that have no purchase history does Kobo supply recommendations based on text. The purpose of this project is to improve its text-based similarity analysis to provide better recommendations for all titles regardless of popularity and genre, as well as for all users who want recommendations that better reflect their purchases. Through this project, Kobo will benefit from an enhanced recommender system, and in effect, an improved customer experience and an increase in purchase conversion.

Faculty Supervisor:

Murat Erdogdu

Student:

Peilin Sun

Partner:

Rakuten Kobo Inc

Discipline:

Computer science

Sector:

University:

University of Toronto

Program: