Skip to main content
This summary presents the observed win-rate performance from machine learning experiments using the spreads listed here. Experiment goal:
Identify option spreads with a high probability of hitting a defined profit target.
Two profit targets were tested: Testing was conducted using three independent datasets (Month 1–3) to ensure robustness across different periods.

1. Simple Takeaway

Across several months of trade simulations, filtering models produced consistently high win-rates for common option spread strategies.

Win-Rate Summary

Key Observations

  • Bear Call Spread: Most consistent win-rate; retained strength even at 50% target
  • Bull Call Spread: Very strong for 30% exits; a bit lower at 50%
  • Bear Put Spread: Stable above 90% for 30% targets; slight drop for 50%

What This Means

The filtering models identify spreads that have historically reached profit targets with high consistency—focusing on high-probability trades over predicting large moves.
This means consistency over speculation.

2. Expanded Results

Win-rates by strategy, split by profit target and month:

30% Profit Target

50% Profit Target

Interpretation

  • Stability: Results were consistent across all datasets—not due to chance.
  • Profit Target: Higher targets (50%) reduce win-rate, but probabilities remain strong.
  • Strategy Strengths:

Final Note

These results reflect historical model performance using defined filters and profit targets.
They show the filtering system can identify high-probability spreads, but do not guarantee future results.
BigDipperOptions helps traders spot structured opportunities, not provide investment advice. Options trading involves risk. Past performance is not indicative of future results.