EXP-000003
Positive-month share as a consistency score input
Hypothesis
Share of profitable months is a usable consistency measure for these systems as-is.
Controlled change
None shipped in this form — the raw share was evaluated and rejected as a standalone input.
Dataset & conditions
Extracted monthly series, all 14 systems.
Before / After
Before
- Systems posting 90%+ positive months
- 9 of 14
After
- Among them, systems with a 40%+ drawdown
- 4
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
Grid- and martingale-style exits win almost every month by construction and give it back in one. Rewarding the raw share ranks the riskiest builds highest — the opposite of what a consistency score is for. Replaced by share × worst-month factor.
AI involvement
- Model
- Claude (Anthropic)
- What AI did
- Proposed the raw share as a consistency input and then produced the counter-analysis that rejected it; the rejection was a joint decision.
- 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.
Notes
The replacement is EXP-000004.
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.