A selection of my work demonstrating expertise in:

Each project showcases how I apply these analytical techniques to solve real-world problems.

 

I. Predictive Modeling (Classification & Regression)

These projects showcase supervised learning algorithms (XGBoost, Random Forest, Regression) to predict outcomes, quantify risk, and guide strategic decision-making.

Credit Risk Prediction Model

  • Problem: Predict credit risk to help financial institutions make informed lending decisions.
  • Approach: Built a machine learning model using XGBoost and Random Forest, with feature engineering and model evaluation.
  • Technologies: Python, XGBoost, Random Forest, Azure, Power BI
  • Results: Delivered a predictive model that identifies high-risk customers with high accuracy.
    View on GitHub

Housing Price Prediction

  • Problem: Predict housing prices to help buyers and sellers make informed decisions.
  • Approach: Random Forest regression with feature engineering and extensive EDA.
  • Technologies: Python, Scikit-learn, Pandas, Matplotlib
  • Results: Accurate predictions for housing prices based on key property features.
    View on GitHub

 

II. Time Series Forecasting & Simulation

Demonstrate capability in modeling time-dependent data and using simulations to predict resource demand and future scenarios.

Healthcare Resource Forecasting

  • Problem: Forecast healthcare resource needs to improve planning and reduce shortages.
  • Approach: Used ARIMA and Monte Carlo simulations to model patient inflow and resource demand; visualized results with interactive dashboards.
  • Technologies: Python, ARIMA, Monte Carlo, Plotly
  • Results: Enabled hospital administrators to anticipate demand and allocate resources efficiently.
    View on GitHub

 

III. Data Visualization, Business Intelligence & App Deployment

Projects that turn complex data into clear, actionable insights via dashboards and apps.

Operations Efficiency Dashboard

  • Problem: Improve operational efficiency through real-time analytics.
  • Approach: Collected and cleaned operational data using SQL and Python automation, and built interactive Power BI dashboards for scenario-based reporting.
  • Technologies: Python, SQL, Power BI
  • Results: Reduced reporting time by 70% and improved decision-making speed.
    View on GitHub

Food Choices Streamlit App

  • Problem: Understand college students’ food preferences for nutritional insights, and deploy an accessible interface.
  • Approach: Built an interactive Streamlit app to collect, analyze, and visualize data.
  • Technologies: Python, Streamlit, Pandas
  • Results: Allowed users to explore trends interactively and demonstrated end-to-end application deployment skills.
    View on GitHub

 

✨ For more projects, visit my GitHub repositories