AI Case Study

"Artificial intelligence (AI)-powered systems provided more accurate predictions for NHL hockey game winners than Vegas betting markets over an extended length of time, according to a press release from Unanimous AI on Tuesday.

In the study, researchers used Swarm AI, a technology that is able to accurately predict results over a slew of markets, including sports, politics, and finance, according to a press release. Swarm AI used predictions data from 25 to 35 average sports fans in real-time, optimizing insights with intelligent algorithms, said the release.

The system generated predictions for 200 NHL hockey games over a 20 week period in the 2017-18 season. While Vegas oddsmakers' predictions ended up being 55% accurate, Swarm AI reached 61% accuracy for the same games, said the release. Additionally, Swarm AI was used to simulate wagering protocol that placed equal bets on the predictions. The simulation garnered a +22% return on investment (ROI) across the games, added the release.

Swarm AI also created a "pick of the week" for all 20 weeks, and achieved 85% accuracy and 170% ROI. The results are a huge success for Swarm AI, especially since it outperformed the accuracy of Vegas betting markets, said the release. Swarm AI's results are fully articulated in the "Artificial Swarm Intelligence versus Vegas Betting Markets" paper.

"The results of this study are extremely promising," said Gregg Willcox, director of research at Unanimous AI and a co-author on the full sports forecasting paper, in the press release. "And while it's fun to predict sports, we are currently applying the same techniques to a wide variety of other domains, including financial forecasting, business forecasting, and medical diagnosis, all with positive results."