- Related Coursework: Quality Management, Supply Chain Analytics, Business Consulting Analytics, Product Management
Nefeli Zafeiri
Business Analytics, Data Strategy, Operations
MSBA at the University of Miami with a background in international business, finance, and data analytics. Passionate about translating data into actionable strategy.
Education
Experience
- Designed and built the documentation website for Ravix, an open-source Python regression library accompanying a Springer-published textbook, responsible for design and content
- Designed and built businessregression.com, the companion site for the same Springer-published textbook, organizing dataset downloads, chapter summaries, and worked regression examples for student use
- Completed an independent directed study supporting the professor's book project (research support, edits)
- Support a professor who oversees the MSBA program with undergraduate course assistance and student guidance
- Manage communications, follow-ups, and academic tasks to keep coursework and provide operational support
- Identified budget inefficiencies that reduced unnecessary event costs and improved resource utilization
- Improved financial efficiency across athletic events by analyzing budget variances and supporting resource allocation
- Reduced budget adjustments by flagging potential issues earlier in the event planning cycle
- Achieved 1st place at Oklahoma Research Day 2025 for a regression-based analysis of natural gas price behavior
- Analyzed weather and forecast datasets in Excel to quantify their influence on natural gas price movements
- Interpreted analytical findings to support financial forecasting and inform energy market decision-making
- Developed predictive models using regression and time-series techniques to identify long-term market trends
- Analyzed customer demand and product-mix trends to optimize inventory, shifting resources toward high-demand items and reducing low-performing SKUs
- Expanded brand visibility by 25% by assisting with promotional campaigns and community events
- Negotiated pricing and delivery terms with suppliers and customers, improving cost efficiency and partnerships
Projects
AI-Driven Wildfire Risk Monitoring
Developing an AI solution for wildfire risk monitoring and early detection in collaboration with Deloitte, translating geospatial and environmental analytics into actionable insights for real-world decision-making.
Chart Reasoner, Fine-tuned Phi-3 Mini
My first published AI model: a LoRA fine-tune of Microsoft's Phi-3 Mini (4k) for chart reasoning, extracting structured insights from chart images. Trained with Unsloth + TRL and released on the Hugging Face Hub as a component of the SQL Agent stack.
SQL Agent, Natural Language to SQL
A multi-model AI agent that accepts a natural-language question, generates and executes the corresponding SQL query, and returns an interactive data visualization. Three open-source LLMs were fine-tuned on a 761K-row curated dataset for SQL generation, chart reasoning, and SVG rendering, then deployed end-to-end on Hugging Face Spaces.
Coffee Shop Big Data Analytics
End-to-end big-data ML project on ~1.8M coffee-shop transactions. PySpark for ingest, cleaning, and EDA; scikit-learn + XGBoost + Optuna for modeling; SHAP for explainability. Delivered regression and classification models with clear lifts over baselines (wait time +34.8%, purchase amount +11.8%, rewards-target AUC 0.98).
Time Series Forecasting Comparison
Compared classical forecasting models, ARIMA, ARIMAX with exogenous regressors (layoffs, quits, sales, wages), Naive, and a Hybrid OLS+ARIMA, against a 12-month moving average baseline on monthly economic data. The simple moving average produced the lowest MAPE; a useful reminder that complexity isn't always better.
Customer Prediction with XGBoost and SHAP
End-to-end binary classification project predicting customer behavior. EDA and preprocessing through gradient-boosted modeling with XGBoost, then SHAP values to explain individual predictions and overall feature importance. Final deliverable was a research poster.
Monthly Budget App
Multi-month personal budgeting tool in Python with categorized expense tracking (needs vs wants), savings-goal progress, and data visualizations, pie chart by category, line chart over time, seasonal patterns, plus personalized tips against the 50/30/20 budget rule.
Activities and Interests
- Won a scholarship in data visualization demonstrating strength in analytics and business strategy
- Represent the MSBA program, supporting initiatives to improve student engagement and collaboration
- Awarded Top-2 line-up positions throughout college tennis career while leading a team of 6 to 12 players
- Represented the university at major regional and national NCAA tournaments, competing against top-ranked athletes
- Organized and coordinated community service initiatives supporting student-athlete welfare
- Contributed to enhancements of Athletic Department programs for student-athletes
- Represented Greece as a member of the National Tennis Team at an international multi-sport competition