Joint SPX/VIX Calibration Follow-Up: Bates SVJ Degenerates on Daily Data, HMM Fails on Novel Crises, and One Logic Fix Recovers $300K — Findings 7–10

Navnoor Bawa | navnoorbawa.me | March 28, 2026

Three days ago I published The Holy Grail of Volatility Modelling: What Happens When You Actually Try to Build It. That piece documented Findings 1–6: Heston hitting its correlation boundary at ρ=−0.99 during live SPX/VIX joint calibration, path-dependent volatility beating GARCH at 2×, an XGBoost regime classifier reaching 86.95% accuracy on the 2020–2…