For many, predicting future stock prices seems like little more than rolling the dice. But it turns out, something as simple as electricity use can anticipate next year's returns.

According to researchers at the University of Notre Dame, industrial electricity use is negatively correlated with the following year's stock returns.

"For example, if the industrial electricity usage this month is 1 percent lower than that in the same month last year, we predict the stock market return to be 0.92 percent higher in the next year," Zhi Da, a professor of finance at the University of Notre Dame, explained in a press release.

Da says the newly illuminated correlation supports what's called the "counter-cyclical risk premium," which is the idea that it is best to double down on investment during a recession.

Some economists use similar theories to advocate for the federal government's use of progressive taxation during boom times, while upping federal expenditures and make infrastructure investments during slack periods.

Businessman, investor and philanthropist Sir John Templeton famously said: "The best time to invest is when there is blood in the streets."

Da says that industrial electricity output is an especially good business cycle indicator because it can't be easily or cheaply stored. It must be used.

"As a result, industrial electricity usage can be used to track production and output in real time," Da said. It's extra useful, he pointed out, for tracking especially cyclical industrial sectors, like steel and machinery.

Da says that while the new work focuses on industrial electricity, he suggests other indicators could potentially work just as well.

"The notion of counter-cyclical risk premium suggests that any other good business cycle measures should also predict stock market performance," he said. "We study several such measures based on the industrial production in our paper. Compared to these well-known business cycle indicators, which may take several months before they are announced, the electricity usage data is available in almost real time."

The research is set to published in the Journal of Financial and Quantitative Analysis.