Emil Rudobeck

Background

About Emil Rudobeck

Data scientist with 10+ years of expertise in advanced statistical modeling, machine learning algorithms, and research. I have developed predictive models to improve healthcare outcomes in very large CMS datasets, authored hypothesis-driven scientific publications with multilevel models with small datasets, and have presented my research findings at national conferences.Unreliable inputs produce unreliable outputs even with the most sophisticated models. Great models require good data. And good data depends on understanding the goals of the analysis and envisioning the entire process. I enhance model accuracy by first focusing on the quality of input data, which includes deciphering and interpreting analytic goals among stakeholders, sourcing the right data, meticulously exploring and cleaning that data, and applying methodically designed models.Using data-driven insights, I often put stalled projects back on track. With extensive experience in both academic research and industry, I guide complicated projects and bridge the gap between collaborators at all levels by effectively communicating complex ideas and technical topics, allowing for faster development.I have a track record of automating and optimizing analytic pipelines, often refactoring code to consolidate seemingly separate projects into one. This significantly cuts down the time required to run and maintain cyclical production codes. To maintain the achieved optimizations, I also guide software engineers with coding and analytic best practices to ensure that project code remains traceable and maintainable, and computations reproducible.My domain knowledge spans clinical data, CMS/healthcare databases, research, experiment design, and scientific publications. I also have extensive experience in neuroscience, in vitro electrophysiology, and radiation biology.Tools include: • SAS/Viya/Enterprise Guide• Databricks• SQL/Hive• R/RStudio• Python/Jupyter NB• Regular Expressions• SPSS• GraphPad Prism• VSCode• GithubStatistical proficiency includes: • Machine learning algorithms• Linear mixed models/multilevel models• Generalized estimating equations• Dimension reduction• Model training, cross-validation, and statistical tests of model accuracy• Effect size and power calculations• Resampling methods• Ensemble methodsMy interests span robotics, AI, and quantum computing. I am always looking for intellectually challenging analytic projects with a big impact on the world, regardless of domain or geographic location.Email (b64): ZW1pbC5ydWRvYmVjaytsbms2NEBnbWFpbC5jb20=