当AI顾问意见一致：区分预测风险与预测可靠性
原标题：When AI Advisors Agree: Distinguishing Forecast Risk from Forecast Reliability
AI 摘要
该研究基于 iPulse AI 平台 2026 年 4 月至 7 月四个批次、232 个资产、928 份已完成的一季度预测，检验 AI 顾问团预测分歧与预测可靠性之间的关系。结果显示，分歧最低四分位的平均绝对收益误差为 10.31 个百分点，最高四分位升至 21.05，但简单的「价格不变」基线也呈现几乎相同的上升（9.89 到 21.15）。按历史波动率筛选预测的误差（7.97）低于按分歧筛选（10.31）；方向一致性与方向准确率正相关，却伴随更大的收益幅度误差。作者据此区分资产风险、方向共识与收益精度三个常被混为一谈的问题，认为一致性并非预测可靠性的通用证明。
正文节选
When AI Advisors Agree: Distinguishing Forecast Risk from Forecast Reliability 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 framework