EXP-000006
Correlation minimum-overlap rule
Hypothesis
Pairwise correlations computed over few shared months are noise and should not be displayed.
Controlled change
Pearson r rendered only when a pair shares ≥ 24 months; thinner pairs display an em dash.
Dataset & conditions
Extracted monthly series; 91 possible pairs across 14 systems.
Before / After
Before
- Pairs computable with no minimum
- 91
After
- Pairs surviving the 24-month rule
- 78
Validation
Out-of-sample, walk-forward, Monte Carlo and forward results are shown only where they exist as data. None exist for this entry.
Decision
The 13 suppressed pairs involve short-window systems whose r estimates would swing wildly with 1–2 months of data. Surviving range: −0.56 to +0.49, median 0.07.
AI involvement
- Model
- Claude (Anthropic)
- What AI did
- Implemented the correlation floor and the em-dash rendering for thin pairs; the 24-month minimum itself was set by a human.
- Human review
- ✓ Reviewed and approved by a human
AI-assisted entries are published only after human review; entries generated by AI without that review are withheld by the build pipeline. AI does not predict markets, and no entry claims otherwise.
Backtest improvement does not imply future improvement. The more experiments run, the more likely some succeed by chance — this log exists partly so that multiple-testing risk stays visible instead of hidden.