By Dana Yamashita

Machine learning is defined as “an area of artificial intelligence concerned with the development of techniques that allow computers to ‘learn.’” More simply put, machine learning helps machines automatically learn by using past data and adjust their decisions or performance appropriately.

Malik Magdon-Ismail, professor of computer science, and expert in machine learning, data mining, and pattern recognition, is using county data available through the New York State Department of Health and Mental Hygiene to develop models that can predict local aspects of COVID-19, such as the rate of infections over time, the infectious power of the pandemic, the rate at which mild infections become serious, and estimates for asymptomatic infections.

Working with small cities, like the Capital Region, is challenging as there are fewer data points available and information is updated less frequently than the nation as a whole, or an epicenter like New York City. Magdon-Ismail is using an at-risk population of 855,000 to estimate that daily confirmed infections will peak at 1,490 on June 8 with 50% of people staying home, or 750 on May 28 with 75% staying at home.

“There are no simple, robust, general tools that, for example, officials in Albany could use to make projections,” said Magdon-Ismail. “These models show that the projections vary enormously from one city to another. This knowledge could relieve some of the uncertainty that is around in developing policy.”

Magdon-Ismail shared that there are many different models and explanations that are basically as good, so he focuses on simple models and uses “robust” algorithms to incorporate solutions beyond that of the mathematical ideal.