Machine learning augmentation reduces prediction error in collective forecasting: development and validation across prediction markets

Author:

Gruen Alexander,Mattingly Karl RORCID,Morwitch EllenORCID,Bossaerts FrederikORCID,Clifford Manning,Nash Chad,Ioannidis John P AORCID,Ponsonby Anne-LouiseORCID

Abstract

AbstractThe recent COVID-19 crisis highlighted the inadequacy of human forecasting. We aim to leverage human prediction markets with real-time machine weighting of likely higher accuracy trades to improve performance. The crowd sourced Almanis prediction market longitudinal platform (n=1822) and Next Generation Social Science (NGS2) platform (n=103) were utilised. A 43-feature model predicted top quintile relative Brier accuracy scores in two out-of-sample datasets (pboth<1×10−9). Trades graded as high machine accuracy quality vs. other trades had a greater AUC temporal gain from before to after trade. Hybrid human-machine forecasts had higher accuracy than human forecasts alone, particularly when the two systems disagreed by 5% or more for binary event prediction: the hybrid system demonstrating substantial AUC gains of 13.2%, p=1.35×10−14and 13.8%, p=0.003 in the out-of-sample Almanis B and NGS2 datasets respectively. When discordant, the hybrid model was correct for COVID-19 event occurrence 72.7% of the time vs 27.3% for human-only models, p=0.007. This net classification benefit was replicated in the separate Almanis B dataset, p=2.4×10−7. Real-time machine classification followed by weighting human trades according to likely accuracy improves collective forecasting performance. Implementation may allow improved anticipation of and response to emerging risks and improved human collective efforts generally.Significance StatementHuman-machine hybrid approaches have been identified as a new frontier for event prediction and decision making in the artificial intelligence and collective human intelligence fields. For the first time, we present the successful development and validation of a human-machine hybrid prediction market approach and demonstrate its superior accuracy when compared to prediction markets based on human forecasting alone. The advantages of this new hybrid system are demonstrated in the context of COVID-19-related event prediction.

Publisher

Cold Spring Harbor Laboratory

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3