π MS in Information Technology & Analytics from Rutgers Business School - Newark
π International student | Open to full-time roles in the U.S. (sponsorship needed starting 2028)
πΌ Actively seeking roles in Anti-Money Laundering (AML), Risk Analytics, Data Analysis, Business Intelligence, and Tech
π Connect with me on LinkedIn
- π§ Passionate about data-driven storytelling and real-world impact
- π Skilled in Anti-Money Laundering (AML), Financial Data Analysis, Data Engineering, Business Intelligence, Compliance, and Analytics
- π‘ Experience working on fraud detection (Airbnb), cost optimization (healthcare), and churn prediction projects
- π± Currently learning: Alteryx, Power BI Advanced, and ML for Risk Modeling
- βοΈ Fun fact: I enjoy simplifying complex data into actionable dashboards and visuals!
Languages: Python, R, SQL, HTML/CSS, SAS
Libraries: Pandas, NumPy, Scikit-learn, Matplotlib, Seaborn
BI Tools: Power BI, Tableau, Excel, WorldCheck, Jupyter
Automation: Alteryx (Fundamentals Completed), Airflow, Apache Spark, Apache Beam
Cloud & Data: Snowflake, GCP, AWS, Azure, Docker, Kubernetes, Terraform, MySQL, PostgreSQL, MongoDB, AlloyDB, Oracle, Amazon S3, Redshift
Version Control: Git, Bash, GitHub
Project Title | Tools Used | Highlights |
---|---|---|
Uber Trip Analysis | Python, Pandas, Jupyter | Visualized NYC Uber trip patterns and peak-hour demand trends |
Air Pollution Analysis | Tableau, Excel | Visualized global pollutant trends and regional disparities over time |
Healthcare Cost Optimization | Excel Forecasting | Achieved 18% cost savings using break-even & dosage trend analysis |
Titanic ML | Python, Scikit-learn, ML Models | Predicted passenger survival using classification techniques |
StackOverflow Forecast | Python, ARIMA, Holt-Winters | Forecasted Python-related questions on Stack Overflow |
NJ Home Price Forecasting | R, Holt-Winters, ggplot2, forecast | Predicted housing price trends in New Jersey using time series models |
DC Industries Sales Optimization | Alteryx, Excel, ETL | Automated ETL to merge regional sales data, identified underperforming categories, and reduced manual reporting by 40% |