Amplifying group intelligence by adaptive population optimization

A method for curating an optimized population of human forecasting participants using data collected from a baseline population of human forecasting participants, the system performing a software-based analysis identifying a likelihood that each participant will be an accurate forecaster without a need for historical accuracy data, comprising the steps of:

• presenting, by an analysis processing device including a processor and configured for networked communication, to each baseline population participant via an application instance in network communication with the analysis processing device and configured to interact with that participant, a set of possible outcomes for each of a set of future sporting events, wherein each set of possible outcomes for each future sporting event has at least two possible outcomes;
• collecting a set of predictions from each baseline population participant via the application instance, wherein each set of predictions includes, for each future sporting event in the set of future sporting events, one possible outcome selected from the set of possible outcomes for that future sporting event, and wherein an actual outcome of each of the future sporting events is unknown at the time of collecting;
• storing, in a Participant Prediction Dataset stored on at least one data storage set in communication with the analysis processing device, the set of predictions from each baseline population participant in association with that baseline population participant;
• computing, by the analysis processing device for each future sporting event in the set of future sporting events, at least one outcome support value for each possible outcome of that future sporting event, wherein each outcome support value is based at least in part on a percentage of baseline population participants that selected that possible outcome for that future sporting event;
• computing, by the analysis processing device for each baseline population participant, a set of outlier scores comprising an outlier score for each future sporting event, wherein the outlier score for the future sporting event is computed by algorithmically comparing the participant's selected outcome for that future sporting event to the outcome support value for that possible outcome of that future sporting event, whereby the outlier score indicates how well that participant's selection aligned with the selections collected from the baseline population for that future sporting event;
• storing each set of outlier scores in the Participant Prediction Dataset in association with that baseline population participant;
• determining, by the analysis processing device for each baseline population participant, an outlier index based on the set of outlier scores computed for that participant, wherein the outlier index indicates how well the set of that participant's selections aligned with the selections collected from the baseline population;
• curating, by the analysis processing device, an updated population of participants, based at least in part upon a plurality of the outlier indexes comprising applying a weighting value to each of the baseline population participants based at least in part upon a plurality of the outlier indexes, wherein the applied weighting values are lower for participants with the outlier index indicating low alignment with the baseline population and the applied weighting values are higher for baseline population participants with the outlier index indicating high alignment with the baseline population participants;
• and
• storing the weighting value in association with each participant on the at least one storage device, wherein the weighting values are accessible by at least one software process for use in generating a statistical group prediction for at least one sporting event of the group of sporting events.