At Jalpa Plastic, I built a Python and Power BI dashboard analyzing Germany’s solar PV market. I turned regional and segment-level demand data into a reusable reporting model for outreach planning and validated it against public regulatory sources.
On my E-Commerce Customer Churn & Revenue Risk Analysis project, I analyzed 5,630 customer records with RFM segmentation and a Random Forest classifier. The analysis quantified €152,031 in revenue at risk, and I translated the findings into a three-page Power BI dashboard with retention recommendations.
At Little Master Educational Institute, I cleaned and analyzed a dataset of more than 10,000 records, identifying five performance gaps that informed strategy decisions. I also built 12 interactive Power BI dashboards, automating reporting and cutting reporting time by 20%.
My other work includes a SQL and Python star-schema data warehouse, and CNN + LSTM models for sign language recognition at BISAG-N. I use SQL, Python, Power BI, and Tableau for analysis, data validation, and reporting.
