I've built end-to-end data projects that transform customer and business data into clear insights and predictive models. My work spans SQL-based ETL, Power BI reporting, Python analytics, and machine learning.
For a telecom churn analysis project, I engineered a SQL Server ETL pipeline for 6,000+ customer records and created an executive Power BI dashboard tracking a 27.0% churn rate and demographic drivers. I also trained a Random Forest model to identify high-risk churn customers.
I've developed a fake-news detection pipeline using NLP, TF-IDF, and Logistic Regression, and analyzed more than 10 years of Amazon bestseller data using Pandas, NumPy, and Matplotlib. Through Deloitte Australia's virtual experience, I built a Tableau dashboard and cleaned and analyzed corporate datasets in Excel.
In JPMorgan Chase & Co.'s quantitative research virtual experience, I used Python Logistic Regression to model credit risk and applied dynamic programming to bucket FICO scores into risk segments. I'm pursuing a Bachelor of Engineering in Information Technology with a 9.19/10 CGPA.
