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.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Artificial Human Swarms Outperform Vegas Betting Markets


    Contributors:


    Publication date :

    2018-10-18


    Size :

    9 pages





    Type of media :

    Article/Chapter (Book)


    Type of material :

    Electronic Resource


    Language :

    English





    Betting on ballast

    Wanek, Mischa | IuD Bahn | 2006


    Scalable Human Interaction with Robotic Swarms

    Pendleton, Brian / Goodrich, Michael | AIAA | 2013


    Betting On Better Batteries

    Online Contents | 2013


    WHY NA BATTERIES COULD OUTPERFORM LI ONES

    Gaubicher, Joël / Moreau, Philippe / Cuisinier, Marine et al. | British Library Conference Proceedings | 2014