7/26/2023 Bruce Adams
Have you ever wondered why your streaming service recommends a particular movie to you? Hanghang Tong, Associate Professor of Computer Science, received an Amazon Research Award as part of Amazon Science’s Fall 2022 cohort of awardees for researching that process.
Written by Bruce Adams
Have you ever wondered why your streaming service recommends a particular movie to you?
Hanghang Tong, Associate Professor of Computer Science, received an Amazon Research Award as part of Amazon Science’s Fall 2022 cohort of awardees for researching that process.
The topic Tong successfully proposed was “Graph algorithms for personalized recommendation in Prime Video.” He has described his research interests as “Large scale data mining and machine learning, especially for graph and multimedia data with applications to social networks analysis, healthcare, cyber-security, and e-commerce.” This explains the success of his proposal, with Amazon Science aiming “to improve engagement by providing relevant, personalized, and timely recommendations.”
As Tong explained, “Amazon has many interesting application scenarios (e.g., recommendation) and data (e.g., knowledge graphs) that align with our research interest very well. One of my current research projects, fair network learning, is co-sponsored by the National Science Foundation (NSF) and Amazon through its fairness in AI program. Algorithmic fairness is one of my recent major research foci.”
Tong added, "One thing I want to explore is how to make the recommendation process more transparent and explainable to end users. In other words, in addition to deciding which items to be recommended to a user, we also want to inform the user why the algorithm recommends this item.”
Amazon Research Awards (ARA) provides unrestricted funds and AWS Promotional Credits to academic researchers investigating various research topics in multiple disciplines. This cycle, ARA received many excellent research proposals from across the world and today is publicly announcing 79 award recipients who represent 54 universities in 14 countries.
Recipients have access to more than 300 Amazon public datasets and can utilize AWS AI/ML services and tools through their AWS Promotional Credits. Recipients also are assigned an Amazon research contact who offers consultation and advice, along with opportunities to participate in Amazon events and training sessions. Tong noted that “the datasets will help verify and validate the prototype algorithms we develop, and the AWS resource Amazon provides to us will accelerate this process.”
Additionally, Amazon encourages the publication of research results, presentations of research at Amazon offices worldwide, and the release of related code under open-source licenses. Tong affirmed that “I have previously collaborated with Amazon and the Prime Video group, which I really enjoy. I would love to continue and expand the collaboration.”