Temporal Dynamics in Recommender Systems

PhD Thesis Proposal Defence


Title: "Temporal Dynamics in Recommender Systems"

by

Mr. Zhongqi LU


Abstract:

We investigate the temporal dynamics phenomenon in recommender systems. By 
analyzing the public dataset from real world applications, we find the temporal 
dynamics phenomenon is common in the online recommender systems, and the 
phenomenon would cause problems in making good recommendations. In this 
proposal, we propose two approaches to tackle the problems caused by the 
temporal dynamics phenomenon, i.e. the collaborative evolution approach, and 
the reinforcement learning approach. The collaborative evolution approach is 
motivated by the sequential auto-regression property in the changes of the 
users' interesting. The reinforcement learning approach is inspired by the 
markovian properties in recommender systems. We also proposed the metrics and 
the datasets to verify our proposed approaches in the next stage. In the end, 
we propose a unified framework to include both approaches to handle the 
problems caused by the temporal dynamics phenomenon in the recommender systems.


Date:			Monday, 17 October 2016

Time:                  	2:00pm - 4:00pm

Venue:                  Room 3494
                         (lifts 25/26)

Committee Members:	Prof. Qiang Yang (Supervisor)
  			Prof. Lei Chen (Chairperson)
 			Dr. Yangqiu Song
  			Prof. Dit-Yan Yeung


**** ALL are Welcome ****