Nicholas Brusilow

University of Missouri

• Selected for Best Data Science Week Presentation 2026 by Mizzou faculty
• Built gradient boosting models to forecast daily tire pickup volumes using millions of records of proprietary logistics data
• Engineered temporal and operational features — days since last pickup, weekday effects, rolling averages — that meaningfully improved prediction accuracy
• Ported training pipeline from a local environment to Kubernetes, enabling full-dataset XGBoost jobs on cloud infrastructure

University of Missouri

• Built end-to-end scikit-learn pipelines to predict product backorders on a large Kaggle dataset
• Combined anomaly detection, feature selection, dimensionality reduction, and classification into unified, reusable pipelines
• Compared three approaches: Isolation Forest + Random Forest, Elliptic Envelope + PCA + Logistic Regression, and LOF + Factor Analysis + Naive Bayes

University of Missouri

• Mapped county-level income and crime data using LISA (Local Indicator of Spatial Autocorrelation) and MGWR (Multiscale Geographically Weighted Regression)
• Identified regions where high regional poverty coincided with low regional crime rates — diverging from the broad poverty–crime correlation

Guardian Angel Orthodox Day School — Des Plaines, IL

• Taught mathematics to grades 4–8, building curricula and assessments tailored to mixed-ability classrooms
• Administered MAP standardized testing (fall / winter / spring) and used year-over-year results to identify skill gaps and adjust instruction

Saint Mary of the Angels School — Chicago, IL

• Designed mathematics curriculum for grades 5–8; taught Latin grammar and reading to grades 5–8 (2022–23)

Fellowship of St. James (Christian Publishing Nonprofit) — Chicago, IL

• Managed full-cycle bookkeeping in QuickBooks Online, including payroll, donor records, tax filings, and bank reconciliations
• Analyzed financial and donor data in Excel to track revenue streams and inform fundraising strategy

M.S. Data Science & Analytics — High Performance Computing Specialty  |  GPA: 3.90

Relevant Coursework: Applied Machine Learning, Data Mining & Information Retrieval, Big Data Visualization, Databases & Analytics, Cloud & Distributed Computing

B.A. Mathematics  |  GPA: 3.92, Magna Cum Laude, Phi Beta Kappa

Relevant Coursework: Real Analysis, Abstract Algebra, Linear Algebra, Differential Geometry

Off-Campus Study: German Studies, Berlin (Fall 2019)