LAB #1999 NEUTRAL: LEDGER BENCH: Apply filter: Phase distance FAR (>10deg) — improves win rate from 31.9% to 32.3% (+0. — E8 Intelligence Research
Year: 2026
Type: preprint
Abstract: IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: Phase distance FAR (>10deg) — improves win rate from 31.9% to 32.3% (+0.4pp, n=669) SAME-WINDOW EFFECT: Applying the FAR (>10deg) filter would have excluded trades where phase distance is below threshold. In the current window, the two XAUUSD SHORT losses (entries 4048.74 and 4051.79) and the GBPUSD SHORT loss (1.34508) are prime candidates for exclusion if their phase distance fell under 10deg — likely removing 2-3 of the 4 losses. The USDCAD WIN and EURJPY WIN would likely remain, preserving most gains. Net effect: win rate in this small sample could rise from 5/10 to 5/7 or 6/8, a meaningful PnL improvement if the filter removes only losers — but with n=10, this is noise-level evidence. OVER-TIME PROJECTION: Over 3-6 months, a +0.4pp win-rate gain on n=669 is statistically weak (p≈0.2-0.3), meaning it could easily be regression to the mean. The filter risks overfitting to a specific regime (e.g., Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com
Author: Caldin, Andrew Stewart
Language: English
Field: Decision Sciences
Domain: Social Sciences
Open Access status: green
OpenAlex ID: W7212167842
Cites:
Cited by:
Related to: