Mathematics · Statistics · Data Science
I'm Nanalise Howe, a Mathematics student concentrating in Data Science at Austin Peay State University. My interests lie in statistical modeling, predictive analytics, and applying quantitative methods to financial questions.
About
I'm a Mathematics student concentrating in Data Science at Austin Peay State University, graduating in December 2026.
My primary interests are statistics, data analytics, and predictive modeling, particularly their applications in finance. I enjoy exploring relationships in data, understanding the mathematics behind statistical models, and using quantitative methods to answer real-world questions.
My current research focuses on mortgage prepayment behavior using Freddie Mac loan-level data, where I'm exploring survival analysis to understand the timing and factors associated with early loan payoff.
Outside my main academic focus, I enjoy exploring data engineering and workflow automation. I've experimented with data pipelines and tools such as n8n, which have helped me better understand how data moves from collection and processing to analysis.
Featured analysis
Python · Statistical Modeling · Forecasting · Power BI
Portfolio case study using the IBM Telco dataset to evaluate churn, develop business metrics, and explore forecasts and investment scenarios.
Compared classification approaches for customer churn (reported best AUC: 0.766), developed an 11-metric KPI scorecard, and explored six-month forecasts. Investment returns were scenario estimates, not realized outcomes.
Selected work
Statistics · R
Investigated wage determinants using regression, transformation, model diagnostics, and visualization.
Exploratory Data Analysis
Explored aviation incident data to investigate patterns across time, geography, and incident characteristics.
Machine Learning · NLP
Applied text features and classification methods to examine sentiment prediction and model performance.
Real-World Data Workflow
Developed a workflow to organize meter readings, calculate bills, and streamline communication with tenants. A practical example of reducing repetitive data-processing work.
Technical foundation
Education