Undergraduate at Vanderbilt University who likes turning messy, real-world data into decisions people can act on — from ETL pipelines and forecasting models to the web apps that put the results in front of people.

Right now I'm leading several data-science projects for The Weather Company, and building my own projects to go deeper on machine learning and product engineering.

• Demand forecasting — time-series pipelines that sync from commerce/ERP APIs and forecast demand down to the SKU and size level
• Content & engagement analytics — PCA-based content scoring, completion-rate driver analysis, and correlation studies on what actually moves engagement
• Data products & web — full-stack apps (Next.js / React) that make analysis usable, plus scrapers that turn public web data into clean datasets

• Languages: Python · R · SQL · TypeScript / JavaScript · Java · SAS
• Data & ML: pandas, NumPy, scikit-learn (PCA, regression), NLP (nltk, transformers); forecasting & feature engineering
• Scraping & automation: Selenium, BeautifulSoup, requests; OpenCV for image features
• Visualization: matplotlib, seaborn, Plotly · exploring Tableau & Power BI
• R: tidyverse, dplyr, haven
• Web: Next.js 16, React 19, TypeScript, Tailwind CSS, Vercel
• Workflow: Jupyter, Git
• Certification: SAS Business Analyst

Most live in private repos — happy to walk through any of them.

• Retail demand forecasting — incremental ERP-API sync into a tidy data layer + SKU/style-level demand forecasts for a footwear retailer
• Content performance analytics — PCA content scoring, completion-rate analysis, and push-notification experiments for The Weather Company
• ActCiv — a civic-action web app (Next.js 16) that helps people find their representatives and take action
• Web data scrapers — Selenium / BeautifulSoup pipelines for race-event listings and business directories

• LinkedIn: parker-pape
• Email: parker.w.pape@vanderbilt.edu

Thanks for stopping by!