MODEL ADOPTION #1143: REJECT — LEDGER BENCH: Apply filter: Min confirmations >= 6 — improves win rate from 31.7% to 41.3% — E8 Intelligence Research

Andrew Stewart Caldin

doi:10.5281/zenodo.21989539

August 18, 2026Open Access

MODEL ADOPTION #1143: REJECT — LEDGER BENCH: Apply filter: Min confirmations >= 6 — improves win rate from 31.7% to 41.3% — E8 Intelligence Research

View Full Paper

Ask AI

Bookmark

Share

Key Points

Evaluate whether adopting a static filter requiring at least six confirmations improves long-term model performance without sacrificing signal diversity or adaptability.
Analyzed backtest performance metrics under a static confirmation filter (min confirmations >= 6).
Assessed theoretical alignment with underlying phase and polarity rhythm logic compared to raw confirmation counting.
Evaluated expected impacts across signal sub-types, overall trade frequency, regime shifts, and total profitability.
Applying the filter increased backtest win rate from 31.7% to 41.3% (+9.6 percentage points).
Model adoption was rejected because the filter disproportionately eliminates essential signals (rizzy5m, wkjudas) and risks dropping total PnL by 10-15%.
The static threshold fails to adapt to market volatility, risking degradation over 3-6 months by filtering out profitable fast-velocity entries.

No abstract yet

We only have this paper's title and publication details.

Read it at the source

Implication

Model evaluation demonstrates rejection of a confirmation filter in trading algorithms, suggesting static thresholds risk overfitting despite higher win rates.

Discussion

No takes yet. Share an insight, caveat, or question.

Cite This Study

Andrew Stewart Caldin (2026) studied this question.

synapsesocial.com/papers/6a86b56c8a91293e6a1ccd13 https://doi.org/10.5281/zenodo.21989539

View Full Paper

Ask AI

Bookmark

Share

MODEL ADOPTION #1143: REJECT — LEDGER BENCH: Apply filter: Min confirmations >= 6 — improves win rate from 31.7% to 41.3% — E8 Intelligence Research

Key Points

No abstract yet

Implication

Discussion

Cite This Study

MODEL ADOPTION #1143: REJECT — LEDGER BENCH: Apply filter: Min confirmations >= 6 — improves win rate from 31.7% to 41.3% — E8 Intelligence Research

Key Points

No abstract yet

Implication

Discussion

Cite This Study

Keep reading

More related papers

Keep reading

More related papers