arXiv cs.MA· Russlan Ramdowar·· 6 天前AI 评分23
当 AI 顾问意见一致时：区分预测风险与预测可靠性
When AI Advisors Agree: Distinguishing Forecast Risk from Forecast Reliability
AI 导读
研究基于 iPulse AI 四个生产批次中 232 项资产的 928 份一季度预测，将十种历史 Gemini 配置归入七个投资框架，并与后续市场结果比对。最低分歧四分位的平均绝对收益误差为 10.31 个百分点，最高分歧四分位升至 21.05，但"价格不变"预测的误差也从 9.89 升至 21.15。
正文 · 原文
Abstract:If seven AI advisors give similar forecasts, should we trust them more? Agreement can indicate useful shared evidence, but it can also reflect an asset that was easier to forecast in the first place. We examine this distinction using 928 completed first-quarter forecasts for 232 assets across four production batches of iPulse AI. Ten historical Gemini configurations are grouped into seven investment frameworks; their archived forecasts are compared with later market outcomes, without generating new reports. Mean absolute return error rises from 10.31 percentage points in the lowest-disagreement quartile to 21.05 in the highest. Yet a forecast of no price change shows almost the same increase, from 9.89 to 21.15. The relationship between disagreement and additional forecast error is not resolved after accounting for visible asset risk. Retaining the quarter of forecasts with lowest historical volatility produces lower error than retaining those with least disagreement: 7.97 versus 10.31 percentage points. Agreement about direction behaves differently. When at least six of seven frameworks share a direction, directional accuracy is higher, but return-magnitude error is also larger. These results distinguish three questions often collapsed into one confidence score: how risky the asset is, whether advisors agree on its direction, and how precisely they forecast its return. For this historical council, agreement is informative in specific ways; it is not a general certificate of forecast reliability.
| Comments: | 16 pages, 8 figures, 5 tables. Research artifacts: this https URL. Code and documentation: this https URL |
| Subjects: | Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2610.13431 [cs.MA] |
| (or arXiv:2610.13431v1 [cs.MA] for this version) | |
| https://doi.org/10.48550/arXiv.2610.13431 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Russlan Ramdowar [view email]
[v1]
Fri, 9 Oct 2026 11:34:07 UTC (152 KB)
来源：arXiv cs.MA · arxiv.org