Turning data into decisions that matter.

• Data Analyst: Focused on converting unstructured datasets into automated dashboards and clear, decision-ready insights.
• Education: Completed a Master's in Business Analytics at CSU Fullerton (Dec 2025) with prior BS in Computer Science & Engineering.
• Analytical Mindset: Beyond SQL pipelines and machine learning, I analyze Premier League tactics — finding patterns both on and off the pitch.

• SQL Reporting: Write SQL queries to pull and clean data across multiple tables, supporting stakeholder reporting requests.
• Power BI Maintenance: Maintain existing Power BI dashboards, catching and resolving issues when scheduled refreshes don't run as expected.
• Ad-Hoc Analysis: Use Python and pandas to clean and analyze data for ad-hoc requests from the team, usually 1–2 a week, turning quick business questions into data pulls.

• Data Validation: Cleaned and validated datasets by writing advanced SQL queries to ensure accurate reporting.
• Revenue Analysis: Analyzed a $1M+ sales dataset to surface revenue trends and actionable insights for stakeholder teams.
• Reporting Automation: Cut reporting times by 30% by migrating manual spreadsheets into Power BI and automating core KPIs.
• Churn Modeling: Supported a ~20% retention lift among 100K+ high-risk users by building an A/B-tested predictive churn model in Python.

Segmented 10,000+ retail transactions using RFM analysis and K-Means clustering to identify the customer segment driving $714K — 66% of total revenue — then evaluated Customer Lifetime Value against acquisition cost to assess ROI on further investment.

Built a soft-voting XGBoost + Random Forest ensemble trained on 10 seasons of Premier League data — 3,800+ matches across 34 clubs — outperforming the home-favorite baseline by ~5 percentage points, deployed as a live, interactive dashboard.

Analyzed 319K+ clinical records to train a risk-scoring model that increases early high-risk detection while controlling false-positive rates for medical staff.