Summary
Lucas Childs is a data science researcher and soon-to-be UCSB graduate with nine years of diverse experience applying statistical modeling, machine learning, and domain-informed feature engineering to environmental and educational problems. At Scripps Institution of Oceanography he built an interpretable XGBoost model to estimate Secchi depth with physically motivated features, and his academic projects include a hybrid GNN-RNN spatiotemporal crowd-forecasting system and Box-Jenkins climate time-series work. He blends hands-on coding in Python, R, PyTorch, and SQL with experimental design and LLM integration, having reduced instructor workload by 30% through automated feedback tools at UCSB. Comfortable translating complex analyses for nontechnical stakeholders—whether city planners, students, or funding boards—he also manages budgets and operations for a 100-person surf team, showing unusual breadth across research, teaching, and community leadership. Lucas is especially focused on using analytics for sustainability and social impact, seeking internships that pair technical rigor with mission-driven outcomes.
9 years of coding experience
Bachelor of Science - BS, Statistics and Data Science, Bachelor of Science - BS, Statistics and Data Science at UC Santa Barbara
Spanish, English