Conversational Forecasting Across Large Human Groups Using A Network of Surrogate Agents
This demonstrates that AI-facilitated large-group conversations can improve forecasting accuracy in sports betting, though it is incremental to prior work on Hyperchat AI.
The study tasked groups of 25-30 basketball fans with forecasting 56 NBA games using a Hyperchat AI platform, achieving 62% accuracy against Vegas odds of 50% (p=0.059) and a potential 18% ROI over 12 weeks.
Hyperchat AI is a communication and collaboration architecture that employs intervening AI agents to enable real-time conversational deliberations among distributed human teams of unlimited size. Prior work has shown that teams as large as 250 people can hold productive real-time conversations by text, voice, or video using Hyperchat AI to discuss complex problems, brainstorm solutions, surface risks, assess alternatives, prioritize options, and converge on optimized results. Building on this prior work, this new study tasked groups of 25 to 30 basketball fans with conversationally forecasting 56 NBA games (against the spread) over a 12-week period. Results show that when discussing and debating NBA games (for five minutes each) using a Hyperchat AI enabled platform called Thinkscape, human teams were 62% accurate across the full set of NBA forecasts. This is a significant result versus the Vegas odds of 50% (p=0.059). Furthermore, had the participants wagered on the games, they would have produced an 18% ROI over the 12-week period. In addition, this study found that the conversation rate during each forecast was positively correlated with prediction accuracy. In fact, when excluding the 12 forecasts in the bottom 25th percentile by average conversation rate, the remaining 38 forecasts recorded a 68% accuracy against the published Vegas spread (p=0.017). This suggests that large-scale conversational deliberations, when facilitated by intervening AI-agents, positively impacts accuracy in groupwise forecasting.