Python

Demonstrated Unsupervised Domain Adaptation (UDA) from MNIST to MNIST-M using MMD and Domain-Adversarial Neural Networks (DANN) in PyTorch.

Developed a quantitative framework to model the cash flows and price sensitivity of Mortgage-Backed Securities (MBS). The primary focus is investigating the phenomenon of Negative Convexity—the asymmetric risk profile caused by the embedded homeowner prepayment option.

Developed a model to predict the Bee Hive health using localized weather data and a standardized checklist of health indicators.

A Python implementation of Real-Space Dynamical Mean-Field Theory (R-DMFT) designed to handle non-Hermitian Hamiltonians using IPT impurity solver.

A series of mini-projects implementing Modern Portfolio Theory, volatility modeling, and risk-management strategies using Python and stochastic calculus.

Development of a Python Code for modelling Trajectory Surface Hopping on Ab Initio Potential Energy Surfaces