An academic researcher at MIT has found a way to predict the price of Bitcoins, according to an article put out Tuesday (Oct. 21) from the school’s news service.
With the concept of machine-learning algorithm, essentially teaching a machine to make decisions based on data imputed into its system, predictions about prices that indicate when people should sell their virtual currency can be found. You could also find out the right time to buy, and be a new resource for Bitcoin investors to make money.
“Can we explain the price variation in terms of factors related to the human world? We have not spent a lot of time doing that,” Devavrat Shah, associate professor of electrical engineering and computing science at the Massachusetts Institute of Technology (MIT), said in the article. “But I can show you it works. Give me your money and I’d be happy to invest it for you.”
According to the article, the researcher used “a technique called “Bayesian regression,” they trained an algorithm to automatically identify patterns from the data, which they used to predict prices, and trade accordingly. This technique, over a 50-day-period involving 2,872 trades gave the research team an 89 percent return on investment, the article said.
“Specifically, every two seconds they predicted the average price movement over the following 10 seconds. If the price movement was higher than a certain threshold, they bought a Bitcoin; if it was lower than the opposite threshold, they sold one; and if it was in-between, they did nothing,” the article reported.
“When you get down to it,” Shah said, “you really should be letting the data decide.”