Feb 2025 - Present
Current
New York, NY
Quantitative Researcher | RMBS & CLO
- Residential transition models — Own loan-level models for prepayment, delinquency transitions, and liquidation timing, from research through validation, C++ implementation, and production. Developed a loan-bucketing method to generate CPR vectors for OAS calculations, substantially reducing runtime with minimal CPR aggregation error.
- Prepayment models — Rebuilt the Non-QM prepayment model and developed CRT and Jumbo models. Improved forecast tracking by refining LLPA treatment, refinancing incentives, inflation-adjusted balances, and turnover and burnout dynamics.
- Deep delinquency models — Designed and deployed a deep-delinquency transition framework covering 60/90/120+ day delinquency, foreclosure, and REO, incorporating payment-history and home-price features.
- HECM modeling & portfolio analytics — Designed and deployed HECM CPR models with aging ramps, mortality, and cash-out refinancing curves. Maintain the data pipeline and produce monthly reports that help traders understand bond-level CPR drivers, assess portfolio risk, and compare historical prepayment performance with the HECM universe.
- Model monitoring & AI automation — Automate monthly CPR/CDR and transition-matrix reviews by deal and across the universe using LLM agents to diagnose model performance and propose adjustments. Recalibrate when warranted and explain bond-level drivers to traders.
- CLO relative-value modeling — Develop and maintain rating-specific CLO spread and price models across AAA–B tranches, combining dealer quotes, BWIC covers, transaction data, and collateral metrics to support relative-value analysis.
- CLO model research & validation — Evaluate spline-based and gradient-boosting models, including shape-constrained specifications, in weekly walk-forward out-of-sample tests; compare bond-level research predictions with production outputs.
RMBS · CLO · CRT · Non-QM · HECM · Intex / dv01