Skip to main content

Quantitative research · Structured credit

Howard
Zeng.

Models built to survive contact with real data.

I build explainable, production-grade models for structured credit—loan-level mortgage analytics through CLO relative value, from raw data and factor design to daily risk and portfolio decisions.

Portrait of Howard Zeng

Current role

Quantitative Researcher

LibreMax Capital
New York, NY

RMBS / CLO

Research focus

100M+

Loan-level records processed

End to end

Research → models → risk

01 / Experience

Research in practice

From mortgage modeling to production RMBS and CLO research.

Span

2019–Present

10 roles · 3 countries

Feb 2025 - Present

Current

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

May 2024 - Aug 2024

Data Scientist Intern | Lending Analytics, Pricing Team

  • Built automated dashboards for a $6B home equity portfolio of fixed-rate loans and HELOCs; ran competitive rate analysis with Python and Curinos to support pricing decisions.
  • Built SQL/Python pipelines on Teradata processing 100M+ records, with validation and documentation for recurring lending analytics.

Python · SQL · Teradata · Pricing · Curinos

Jan 2024 - May 2024

Cornell MPS Capstone Project | Asset Pricing

  • Cornell MPS capstone project with Gravity Investments; built rolling and recursive forecasting frameworks in Python/PyTorch using linear, tree-based, and neural models for asset-pricing signal research.

Capstone · Python · PyTorch · Time Series

Jan 2023 - Aug 2023

Financial Data & Model Analyst Intern | Mortgage Modeling

  • Processed and aggregated ~9M single-family mortgage loan records in PostgreSQL and Python, reducing storage size by 91% while preserving key modeling attributes.
  • Developed and validated loan-level mortgage default models with logistic regression, random forest, and XGBoost, with feature binning and hyperparameter tuning.
  • End-to-end mortgage default modeling — data prep through model selection and evaluation.

Mortgage · Python · PostgreSQL · XGBoost

Earlier experience 6 roles

Nov 2022 - Mar 2023

UW Foster School of Business

Seattle, WA

Research Assistant

Sep 2022 - Dec 2022

Huatai Securities

Shanghai, China

Equity Research Intern | Research Institute (Hardware & Software)

Feb 2022 - Apr 2022

China Securities

Beijing, China

Quantitative Research Intern | Derivatives Trading

Sep 2020 - Feb 2021

UW Human Centered Design & Engineering

Seattle, WA

Research Assistant

May 2019 - Jan 2021

iRent

Dublin, Ireland

Mobile Full Stack Developer | Founder & Team Leader

Sep 2019 - Jan 2020

UW Information School

Seattle, WA

Research Assistant

02 / Research

Selected work

Research systems for noisy data, unstable regimes, and decisions that need more than a headline metric.

Flagship research / 01

Python · XGBoost · Pipeline · Walk‑forward

AlphaCycle — Stock Prediction Framework

Modular data/model/report pipeline for multi-horizon equity prediction.

Built a config-driven research framework spanning data ingestion, feature storage, model training, and reporting, with walk-forward validation and regime labels.

Read the case study: AlphaCycle — Stock Prediction Framework

Research system

2015–24

Walk-forward window

Workflow / not performance

01

Data

02

Features

03

Models

04

Reports

03 / Profile

How I work

Research is only valuable when it is explainable, reproducible, and connected to a decision.

Current focus

I build loan-level prepayment, delinquency, and liquidation-timing models across residential credit and HECM, and rating-specific spread and price models across CLO. My work spans data preparation, model development, C++ production, loan-to-deal aggregation, monthly model monitoring, and decision-ready explanations for traders and portfolio managers.

Operating principle

Own the full research loop, make the assumptions legible, and fix the root cause—not the symptom. The standard is not a good backtest; it is a system people can trust repeatedly.

Selected prior contexts

Navy Federal Credit Union · WeiCepts · Huatai Securities · China Securities

04 / Capabilities

Research stack

01

Structured Credit / Modeling

RMBS · CRT (STACR/CAS) · Non-QM · Jumbo · HELOC · HECM · CLO · Prepayment · Delinquency/Default · Liquidation Timing · CLO Spread/Price · Scenario/Stress Testing

02

ML / Statistics

Regression & Spline Models · Competing-Risk & Roll-Rate Models · Random Forest · XGBoost/LightGBM · ARIMA / Time Series · Transformers (BERT) · LLM Agents · Imbalanced Classification · Walk-forward Validation

03

Data / Engineering

Python (Polars/Pandas) · C++ · R (Tidyverse) · SQL (Redshift/SQL Server) · Parquet · Jenkins · PowerShell · Automation/QC

04

Systems / Tooling

Intex · dv01 · Git · Linux · Ray (distributed compute) · Azure · AWS · Teradata · Reproducible Configs · Model Versioning

05 / Background

Education

Cornell University

Aug 2023 - Dec 2024

MPS Applied Statistics — Data Science

GPA 4.08 / 4.3

Large-Scale Machine Learning · Deep Learning · Natural Language Processing · Reinforcement Learning · Stochastic Processes · +4 more

University of Washington

Sep 2019 - Dec 2022

BS Economics — Econometrics

GPA 3.6 / 4.0 · Minor: Applied Mathematics & Data Science

Econometric Theory & Applications · Causal Inference · Data Science for Pricing · Financial Economics · Database Systems (SQL) · +4 more

06 / Contact

Let’s talk
research.

Open to quantitative research opportunities and rigorous problems at the intersection of markets, statistics, and production systems.

haozhe76@outlook.com