Aleksandra Cerekovic
|
Data Scientist
Walmart Global Tech |
|
Aleksandra is a Data Scientist at Walmart Global Tech in Sunnyvale, California. Before joining Walmart, she worked as a PostDoc at the University of Zagreb, Croatia where she completed her PhD. Aleksandra has closely collaborated with Idiap Research Institute, in Switzerland where she worked on human conversational behavior understanding using machine learning models. Currently, as a part of the Walmart personalization team, she's developing scalable recommendation algorithms leveraging customers past and present activity on the Walmart’s online shopping site.
|
Workshop: Recommender Systems
August 25, 2021; 10:15-11:00am, PST
August 25, 2021; 10:15-11:00am, PST
Recommender systems are playing a major role in e-commerce industry. They are keeping users engaged by recommending relevant content and have a significant role in driving digital revenue.
Following tremendous gains in computer vision and natural language processing with deep neural networks in the past decade, the recent years have seen a shift from traditional recommender systems to deep neural network architectures in research and industry.
In this workshop, we focus on temporal domain from perspective of both traditional recommender systems and deep neural networks. We first start with the classic latent factor model. We introduce temporal dynamics in the latent factor model and show how this improves performance. We then move into sequential modelling using deep neural networks by presenting state-of-the-art in the field and discuss the advantages and disadvantages.
Following tremendous gains in computer vision and natural language processing with deep neural networks in the past decade, the recent years have seen a shift from traditional recommender systems to deep neural network architectures in research and industry.
In this workshop, we focus on temporal domain from perspective of both traditional recommender systems and deep neural networks. We first start with the classic latent factor model. We introduce temporal dynamics in the latent factor model and show how this improves performance. We then move into sequential modelling using deep neural networks by presenting state-of-the-art in the field and discuss the advantages and disadvantages.
Back to Workshop Instructors