EXP-012 — Connors RSI(2) signal effect and standalone operability
- Run date: 2026-09-17
- Execution model:
v2 - Signal verdict:
signal_positive - Standalone operation verdict:
standalone_hold - Nature: a historical robustness recheck. Not new OOS.
| generated_at | 2026-09-17T00:00:00+09:00 |
The first run was discarded after fixing look-ahead leakage in the control-group candidate filter, and a rerun using only signals before the candidate date was made the canonical version (D-036).
1st (primary) cell
Generalization group of 23 symbols · historical_recheck (2023-01-01~2026-08-26) · normalized_actual_proxy
- Mean event effect: 2.99%
- Monthly block bootstrap 95% interval: [1.53%, 4.36%]
- Strategy trades: 253
- Distinct entry dates: 253 days
- Median exposure per symbol: 7.42%
- Median net expectancy per trade per symbol: 1.06%
Interpretation
Signal effect and standalone operability were judged separately. Periods viewed repeatedly in the past were not called locked OOS, and the results are used only as a robustness recheck before forward observation.
Detailed ledgers: reports/ledgers/EXP-012-summary.csv, EXP-012-benchmark.csv, EXP-012-events.csv.
Source and migration evidence
Source: reports/experiments/EXP-012-connors-rsi2.md
Original SHA-256: bc97944650a53c1d169a8cdb086fa283552f049358307b95857998b76c0101c9
Raw data and account information are not part of the public package. The original results do not replace statistical or scientific revalidation. The English text is a translation; numbers, tables and charts are carried over unchanged.