Subventions et des contributions :

Titre :
A Hybrid Personalized Recommender System for Content Suggestion
Numéro de l’entente :
EGP
Valeur d'entente :
25 000,00 $
Date d'entente :
14 juin 2017 -
Organisation :
Conseil de recherches en sciences naturelles et en génie du Canada
Location :
Ontario, Autre, CA
Numéro de référence :
GC-2017-Q1-00499
Type d'entente :
subvention
Type de rapport :
Subventions et des contributions
Renseignements supplémentaires :

Subvention ou bourse octroyée s'appliquant à plus d'un exercice financier. (2017-2018 à 2018-2019)

Nom légal du bénéficiaire :
Ding, Chen (Ryerson University)
Programme :
Subventions d'engagement partenarial pour les universités
But du programme :

The proposed research is in the area of recommender systems and predictive analytics, and should have anx000D
impact in Canadian ICT (Information and Communications Technology) sector. PostBeyond is ax000D
Toronto-based company providing employee communications solutions to primarily large enterprises. Usingx000D
PostBeyond's product, company employees can have easy access to company-related information through ax000D
central content hub, with the option to share the information externally across their social networks. Thex000D
current solution is one size fit all. Sometimes it could be hard for individual employees to find content they arex000D
particularly interested in and would like to share with others. To solve this problem, in this project, we proposex000D
to build a personalized recommender system that could suggest content for employees to access, consume andx000D
share based on their individual preferences. A few research challenges we must tackle include: 1) the lack ofx000D
historical data on users' content access and sharing patterns; 2) the need to define content profile that is bothx000D
generic and extensible; 3) the need to accommodate users' dynamic behavior into the system; 4) the difficultyx000D
of effectively integrating group recommendation features into the personalized recommendation system. Tox000D
successfully build the proposed recommender system, the following three tasks are identified: 1) developing ax000D
logging tool to save users' content access and social sharing records; 2) applying log mining techniques to minex000D
the user patterns, behaviors and observe the general content consumption or sharing trends; 3) designing andx000D
implementing a hybrid recommender system to do personalized content suggestion and prediction. Thex000D
proposed project could benefit PostBeyond by making their current communications solutions more efficientx000D
and customized towards each individual employee's behavior, and thus a more attractive solution to theirx000D
potential customers. It also drives economic benefits for both PostBeyond and the many Canadian enterprisesx000D
that use their solutions.