• 💻 I’m currently working for the State of Utah
• 🎓 Pursuing my Master of Science in Business Analytics (MSBA)
• 💼 Focus on Data Pipelines, SQL Optimization, Predictive Analytics, Databrick, Pyspark, Python
• ⚡ Fun fact I love breaking down messy data into clean, structured stories

Built a comprehensive end-to-end machine learning pipeline to predict residential property sale prices in Ames, IOWA. This project leverages advanced regression techniques and feature engineering to uncover the key drivers of real estate valuation.

1. Exploratory Data Analysis (EDA): Identified and treated extreme outliers (such as properties with massive living areas but low sale prices) and analyzed target variable distribution (applying log-transformations to handle skewness).
2. Feature Engineering: * Handled complex missing data fields using contextual imputation (e.g., filling missing garage features based on property type).
   • Created unified interaction terms (e.g., combining TotalBsmtSF, 1stFlrSF, and 2ndFlrSF into a singular TotalTotalSF feature).
   • Encoded ordinal quality rankings into numeric scales to preserve structural weight.
3. Model Development & Tuning: Evaluated multiple architectures, balancing bias and variance through rigorous hyperparameter optimization.
4. Ames Housing Price Predictive Framework

Developed an end-to-end predictive machine learning framework to analyze credit risk using complex consumer data.

1. Core Tasks: Data cleaning, extensive feature engineering, and model optimization.
2. Tech Stack: Python, LightGBM, Pandas, Scikit-Learn.
3. Home Credit Default

Student Health Prediction