About Me

I am a member of the Machine Learning Research team at Morgan Stanley, focusing on designing and deploying deep learning models for forecasting and decision-support applications across equity and fixed income markets. My technical work involves developing scalable modeling pipelines, integrating neural network architectures into prediction and time series forecasting models, and leveraging representation learning techniques to improve model performance.

Previously, I worked as a Quantitative Strategist at Goldman Sachs for almost four years, contributing to the development and application of statistical and machine learning models across various financial sub-domains. My academic background is in statistics, and my graduate research focused on high-dimensional time series and graphical models, as well as optimization algorithms.

Broadly, I am interested in developing interpretable models that integrate machine learning and deep learning components to enhance predictive accuracy, while preserving some structural component. At the same time, I am also interested in emerging areas such as retrieval-augmented generation (RAG) and LLM fine-tuning, with a focus on understanding the core frameworks and techniques, and how they can be effectively applied and adapted to other domains. As a trained statistician, I also have a soft spot for causal inference and A/B testing.

Education

• Ph.D., Statistics, University of Michigan
• B.S., Mathematics & Statistics, University of Illinois at Urbana Champaign