Abstract Swarm Intelligence (SI) is a natural phenomenon in which biological groups amplify their collective intelligence by forming dynamic systems. It has been studied extensively in bird flocks, fish schools, and bee swarms. In recent years, AI technologies have enabled networked human groups to form systems modeled on natural swarms. Referred to as Artificial Swarm Intelligence or ASI, this approach has been shown to significantly amplify the effective intelligence of human groups. The present study compares the predictive ability of ASI to Vegas betting markets when forecasting sporting events. Groups of average sports fans were required to forecast the outcome of 200 hockey games in the NHL league (10 games per week for 20 weeks). The expected win rate for Vegas favorites was 62% across the 200 games based on the published odds. The ASI system achieved a win rate of 85%. The probability that the ASI system outperformed Vegas by chance was very low (p = 0.006), indicating a significant result. Researchers also compared the ROI generated from two betting models: one that wagered weekly on the top Vegas favorite, and one that wagered weekly on the top ASI favorite. At the end of the 20-week period, the Vegas model generated a 41% financial loss, while the ASI model generated a 170% gain.
Artificial Human Swarms Outperform Vegas Betting Markets
2018-10-18
9 pages
Article/Chapter (Book)
Electronic Resource
English
IuD Bahn | 2006
|Scalable Human Interaction with Robotic Swarms
AIAA | 2013
|Online Contents | 2013
WHY NA BATTERIES COULD OUTPERFORM LI ONES
British Library Conference Proceedings | 2014
|