EXP-000005
Risk/return map: simple annual average vs CAGR
假设
CAGR compares unequal test lengths more honestly than total-return-divided-by-years.
受控更改
Scatter Y-axis switched to CAGR; caption states the fixed-lot understatement trade-off.
数据集与条件
Extracted balance series, all 14 systems (2–24 years).
更改前 / 更改后
更改前
- RINA simple average (24y, 35× account growth)
- 179%/yr
更改后
- RINA CAGR, same record
- 20.6%/yr
验证
样本外、步进、蒙特卡洛与前向结果仅在数据存在时显示。本条目不存在这些数据。
决定
✓采纳
The simple average produced figures no reader interprets correctly and compressed twelve systems into an unreadable band behind two outliers. CAGR puts 13 of 14 inside 1–28%.
AI 参与
- 模型
- Claude (Anthropic)
- AI 做了什么
- Identified the simple-average distortion on long compounding records and implemented the CAGR replacement with its stated trade-off.
- 人工审核
- ✓ 已经人工审核并批准
AI 辅助的条目仅在人工审核后发布；未经审核的 AI 生成条目会被构建流程扣留。AI 不预测市场，也没有任何条目作此宣称。
回测的改进不代表未来的改进。实验越多，碰巧成功的概率越高——本日志的存在部分正是为了让多重检验风险保持可见。