From time to time, Meta invites academics to propose research in specific areas that align with our mission of building community and bringing the world closer together. To learn about calls for proposals, visit our Research Awards page and subscribe to our email newsletter.
B. Aditya Prakash is an associate professor of computing at Georgia Institute of Technology (Georgia Tech). His research interests include data science, machine learning, and AI, with an emphasis on big data problems in large, real-world networks and time series. His work has applications in the context of computational epidemiology, public health, urban computing, security, and the web.
“A lot of my research stems from working with graphs and sequential data,” Prakash explains. “It has been inspiring to see how we can bring data science and machine learning methodologies to solve problems across a variety of realms — from health care, infrastructure, and public policy to social good. Many of our methodologies are more general, which means we can apply them to diverse problems.”
COVID forecasting using AI models, for example — monitoring peaks and shifts for the CDC and other public communication systems — is one of the more notable projects Prakash and his students at Georgia Tech have undertaken in the past few years. “Forecasting can be difficult to apply in the real world, especially as it must interface with policy and decision-making. Collaborating with external domain experts is a key piece of the puzzle,” he says. “We ask questions like, ‘How do we make forecasts that are actionable and trustworthy?’ For example, with a global pandemic like COVID we have been building tools to understand how disease and disasters spread. This helps experts in sending resources to the correct areas, based on their budget and a forecast of future requirements.”
A strong case study can serve as a powerful tool. When people see the results of our research — or that our insights can answer their questions — they see the value.
Some aspects of Prakash’s research were funded through Meta RFPs, in 2015 and 2021. “Meta is one of the best places in the world to advance machine learning and data science, and collaborating with Meta has been an incredible way to bridge the gap between research and real-world applications at scale,” says Prakash. “This partnership has made it possible to work with people in varied areas — we’re all passionate about driving tangible change at an unprecedented scale.”
After Prakash presented at the Meta-hosted IDSE Faculty Workshop at the Conference on Knowledge Discovery and Data Mining (KDD) in August 2022, he received additional funding from Meta to support his research. “We’re continuously looking to understand new challenges, and I’m excited to incorporate our methodologies into existing Meta forecasting tools,” Prakash notes. “The rich datasets we’re able to work with at Meta offer a tremendous opportunity to make data-driven short- and longer-term predictions at multiple geographical levels. From navigating public health challenges to improving infrastructure and policy, our work is well underway.”