Monday, January 26, 2026 (Eastern Time)
Building an autonomous AI trading system means things break. Here's what we discovered, fixed, and learned today.
LL-309: Iron Condor Optimal Control Research
The Problem: Date: 2026-01-25 Category: Research / Strategy Optimization Source: arXiv:2501.12397 - "Stochastic Optimal Control of Iron Condor Portfolios"
What We Did: - Finding: "Asymmetric, left-biased Iron Condor portfolios with τ = T are optimal in SPX markets" - Meaning: Put spread should be closer to current price than call spread - Why: Markets have negative skew (crashes more likely than rallies)
The Takeaway: - Left-biased portfolios: Hold to expiration (τ = T) is optimal - Non-left-biased portfolios: Exit at 50-75% of duration
LL-298: Invalid Option Strikes Causing CALL Legs to Fail
The Problem: See full details in lesson ll_298_invalid_strikes_call_legs_fail_jan23
What We Did: - Added round_to_5() function to calculate_strikes() - All strikes now rounded to nearest $5 multiple - Commit: 8b3e411 (PR pending merge) 1. Always round SPY strikes to $5 increments 2. Verify ALL 4 legs fill before considering trade complete 3. Add validation that option symbols exist before submitting orders 4. Log when any leg fails to fill - LL-297: Incomplete iron condor crisis (PUT-only positions) - LL-281: CALL leg pricing fallback iron_condor, options, strikes, call_legs, validati
The Takeaway: Risk reduced and system resilience improved
This is part of our journey building an AI-powered iron condor trading system targeting financial independence.
Resources:
- Source Code
- Strategy Guide
- The Silent 74 Days - How we built a system that did nothing
Top comments (0)