A coauthored by researchers at the University of Toronto’s and Google describes an AI technique tailored to health, science, and finance predictions called neural stochastic differential equations (SDEs).
It enables the modeling of random events that might affect a person, price, or the state of a complex system — a system comprised of many parts that might interact with each other. Financial markets and health care networks, for example, are incredibly complex systems. A market trade or a hospital visit would be “random events” that affect those systems. Unlike existing techniques, the authors say, neural SDEs can make predictions about these random events, like what the price of a stock might in the next few days.
One of the most popular existing techniques — neural ordinary equations