Apoorv Kumar Saxena

About Apoorv Kumar Saxena

Driven financial engineering professional with an MS from NYU, currently navigating the steep learning curve as a Senior Quantitative Analyst at Freddie Mac. I\'m passionate about applying econometric models and machine learning to solve complex risk management challenges, having implemented SUR models for macroeconomic forecasting and automated portfolio analysis for thousands of loans. My journey from Electronics Engineering to quantitative finance has taught me the value of continuous learning, leading me to pursue CFA certifications and develop expertise in Python, SQL, and financial modeling.Throughout my career at organizations like Credit Suisse and Freddie Mac, I\'ve been fortunate to work alongside talented teams where I\'ve contributed to meaningful projects. Each challenge, whether implementing FRTB regulations or building ML classifiers with 95% accuracy, has reinforced my belief that success comes from combining technical skills with persistent curiosity and collaboration. I remain committed to growing as a quantitative analyst, eager to tackle new challenges in risk management and contribute to data-driven decision-making in financial markets.

Experience

1. Senior Quantitative Analyst

   Freddie Mac

   Jun 2024 — Present · McLean, VA, US

   Implemented Seemingly Unrelated Regression (SUR) to jointly estimate 8 macroeconomic forecasting equations, extracting residual variance-covariance matrix to capture cross-variable dependencies for correlated shock generation.Applied AR models to forecast a plume of 150 risk scenarios of macroeconomic shocks, using lower triangular Cholesky decomposition of the SUR-derived residual variance covariance matrix and random numbers for portfolio loss mitigation.Classified underwritten loans into market segments based on property income mean growth rate and volatility metrics.Applied Huber robust regression to improve income prediction by 40% within 1-SD compared to the trended mean approach.Calculated the impact of policy change on portfolio expected default cost and stressed default cost due to decrease in DCR of Full-term interest only loans to 1.25x and increases in LTV to 75% by running the model for synthetic loans.Automated portfolio Debt Yield and DCR calculation and visualization on loans enabling data driven underwriting.Mapped the root cause of increasing new acquisition risk by visualizing 4 KRI using monthly and rolling data in Tableau.Built KRI dashboards in Tableau by mapping loans to MSA and borrowers using NLP and classification algorithm.Established model integrity by replicating the data and output consistency for new regime and for successful MRA resolution.

Education

• CFA Institute

  CFA Level 2, Accounting and Finance

  2019 — 2019

• CFA Institute

  CFA Level 1, Accounting and Finance

  2018 — 2018

• New York University

  Master of Science - MS, Financial Engineering

• COEP Technological University

  Bachelor’s Degree, Electrical, Electronics and Communications Engineering

  2014 — 2018