MIT Comes Up with a Formula to Predict Bitcoin Prices


Predicting Bitcoin Price at MIT – Scientists at Massachusetts Institute of Technology (MIT) developed an algorithm that can predict the price of infamously volatile cryptocurrency Bitcoin. The researchers-traders further generated over 9% return off their Bitcoin investments within just two months.

According to MIT News, principal investigator Devavrat Shah and recent graduate Kang Zhang studied the major Bitcoin exchanges for five months, while collecting every second data within the same span. They eventually went home with more than 200 million data points.

Shah and Zhang used a mathematical technique called “Bayesian Regression” to automatically identify the patterns in collected samples. The MIT News writes, “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.”

Their research began to provide fruitful results and eventually earned them a whopping 89% return off their 2,872 trades, the Sharp Ratio being only 4.1.

Shah, who had earlier applied the similar technique on studying Twitter trending topics, confirmed his admiration for the cryptocurrency technology. The MIT-based Assistance Professor accepted to have been “intrigued by the challenge of predicting a currency that has seen its prices see-saw regularly in the last few years.”

Even when the algorithm is currently in its infant stage, the first optimistic results have opened new ways to study Bitcoin patterns. Even Shah believes that this algorithm can be further updated by expanding the scale of data collection, if only provided with proper funds for research.

To contact the reporter of the story: Yashu Gola at