About My Work

I am a PhD candidate in Computer Science at McMaster University, working at the intersection of machine learning and operations research. My research focuses on building data-driven models for decision-making under uncertainty, particularly in systems characterized by limited data, demand heterogeneity, and strong interdependencies.

My work spans clustering-based forecasting for heterogeneous and unbalanced time series, dependence-aware inventory optimization for multi-item systems, and data-driven joint replenishment strategies. I am especially interested in sequential decision-making and MDP formulations, including how deep reinforcement learning can be combined with classical optimization methods to learn robust and practical policies, and how large language models can serve as high-level contextual and reasoning components to enhance robustness, sample efficiency, and interpretability.

With a background in software engineering, and business, I approach ML research with an end-to-end mindset, from data modeling and algorithm design to implementation and operational impact. I work primarily in Python and PyTorch, and I am motivated by problems where machine learning models directly support high-stakes decisions in domains such as healthcare and supply chains.