My Projects

Sales Insights Dashboard

Technologies: Python, pandas, plotly, Streamlit
Description: Developed an interactive dashboard for visualizing sales data by region, category, and time trends. Enabled dynamic filtering and key performance metrics.

Key Insights:

  • Visualized total sales and profits across regions
  • Tracked monthly sales trends and seasonal patterns
  • Highlighted performance by product category
Live Demo GitHub

Customer Churn Analysis

Technologies: Python, pandas, scikit-learn, seaborn, Streamlit
Description: Built a machine learning dashboard to identify key factors influencing customer churn in a telecom dataset. Included performance metrics and feature importance visualization.

Key Insights:

  • Identified top drivers of churn using Random Forest
  • Displayed model performance with classification report and confusion matrix
  • Visualized top 10 features contributing to churn
Live Demo GitHub

US Housing Market Analysis Dashboard

Technologies: Tableau, US Census Data, Interactive Dashboards
Description: Built a comprehensive housing market dashboard analyzing 53 years of US Census data (1963-2016) with interactive regional filtering, price trend analysis, and inventory insights. Features national price appreciation tracking, regional comparisons, and economic cycle visualization.

Key Insights:

  • Housing prices increased 1,670% from 1963-2016, averaging 5.4% annual appreciation
  • Regional housing inventory varies dramatically, creating supply-demand imbalances
  • The 2008 financial crisis disrupted trends but full recovery occurred by 2012-2013
  • National housing data provides comprehensive view while regional data focuses on inventory levels

Live Demo

Baseball Performance Analytics

Technologies: Python, pandas, matplotlib, Streamlit, SQL
Description: Built an interactive dashboard analyzing MLB player statistics using sabermetrics.

Key Insights:

  • Analysizes player perfomances using sabermetrics
  • Predicts outcome based on differnt factors, such as opposing pitcher, and stadium
  • Uses a Machine Learning model to train future predictions and a database
Coming Soon GitHub

Skills Demonstrated

  • Data Cleaning & Processing: pandas, numpy, handling missing data, categorical encoding
  • Statistical Analysis & Machine Learning: Random Forests, model evaluation (classification reports, confusion matrices), train/test split
  • Visualization: matplotlib, seaborn, plotly (bar charts, line charts, feature importance), Tableau
  • Web Applications: Streamlit dashboards with sidebar filtering, expandable sections, and interactive KPIs
  • Databases: SQL, data extraction, datetime transformations
  • Business Intelligence: KPI development, customer segmentation, churn risk analysis, revenue/profit breakdowns, and sales trend forecasting