Know the fundamental asset value. Model the market and manage risk.

My coursework has given me a quantitative framework for evaluating both credit and interest-rate risk. I have applied the Merton structural credit model to estimate distance-to-default, default probabilities, and expected recovery, as well as statistical classification methods to model credit default. In fixed income, I have built and calibrated Black-Derman-Toy interest-rate trees to observed yield curves and used them to value bonds and embedded options under both European and American exercise assumptions.

My MFE has expanded the way I think about equity value beyond traditional fundamental analysis by examining how cash-flow expectations, discount rates, risk premia, and market conditions interact to determine prices. I have used the Campbell-Shiller present-value framework and VAR models to decompose changes in equity valuations into cash-flow and discount-rate components and examine return predictability. I have also explored stochastic discount factor models, Fama-French portfolios, and neural-network approaches to asset pricing, providing a quantitative perspective on why assets earn different returns and how those relationships evolve.

My risk-management work focuses on both measuring financial risk and determining how to hedge it. I have modeled time-varying volatility and tail risk using VaR, CVaR, GARCH, EWMA, and Extreme Value Theory, including backtesting model predictions against realized losses. I have also evaluated derivative hedging strategies under geometric Brownian motion and Heston stochastic volatility, comparing traditional delta-based approaches with adaptive deep-hedging models under transaction costs and changing volatility environments.

My portfolio work has focused on identifying the underlying drivers of asset returns and determining how quantitative methods can simplify complex investment universes. Using Principal Component Analysis and clustering, I have examined common sources of variation across Fama-French equity portfolios and tested whether lower-dimensional representations retain their predictive power out of sample. This work has strengthened my understanding of factor exposures, diversification, correlation structures, and the role of dimensionality reduction in portfolio construction and risk analysis.

Across my projects, I have used statistical and computational methods to translate financial theory into testable models. My work includes Monte Carlo simulation, VAR and GARCH time-series modeling, PCA, k-means clustering, logistic regression, neural networks, numerical optimization, and out-of-sample model validation. More importantly, these projects have taught me to evaluate models not simply by how well they fit historical data, but by their economic interpretation, robustness, predictive performance, and usefulness in real investment and risk-management decisions.