About Me

I'm Ziyang Zhou (周梓洋), a fourth-year Statistics undergraduate at the University of British Columbia (UBC), expecting to graduate in May 2027. My strengths are applied machine learning, statistical modeling and model evaluation. I work across the modeling process: defining prediction tasks, engineering features, training models and testing how well they generalize.

My core toolkit is Python, scikit-learn and gradient-boosted trees, including LightGBM. I apply these methods to forecasting and financial prediction, with particular attention to information leakage, temporal validation and the value of each new feature. In industry, I worked on electricity consumption forecasting at Shusheng Data and GLM-based insurance pricing support at Guangbo.

Beyond tabular modeling, I explore computer vision, model unlearning and LLM-based tools. My projects include CSI 300 stock ranking, RetinaNet model experiments and a local coding assistant. I use AI-assisted development for implementation while taking responsibility for experiment design, model selection and result review; my CPSC 330 machine-learning coursework and CPSC 221 data-structure labs were independently written.