I’m a Data Analyst and Data Scientist specializing in Power BI, advanced analytics, and machine learning, transforming raw data into clear, actionable insights and intelligent solutions.

My journey began with Python, data science, and full-stack development, where a growing curiosity for patterns and predictive modeling led me into business intelligence, statistical analysis, and AI-driven decision systems.

I’ve built interactive Power BI dashboards, end-to-end machine learning pipelines, and Streamlit and Tkinter applications for data exploration, forecasting, and automation. I’m AWS certified with hands-on experience deploying and managing data and application workflows using core cloud services.

I focus on DAX, data storytelling, statistical modeling, and analytical problem-solving, combining machine learning, visualization, and thoughtful design to make complex data accessible, interpretable, and impactful.

image.png

Resume

Contact Me

**Linkedin | Github | Email**

Technical & Professional Skills

icons8-sql-96.png

icons8-python-96.png

Snowflake.png

icons8-tableau-software-96.png

icons8-power-bi-96.png

icons8-excel-96.png

icons8-aws-96.png

icons8-ab-test-96.png

5230749.png

icons8-machine-learning-96.png

⭐ Data Visualization

⭐ Dashboard Design

⭐ Data Transformation

⭐ Report Development

⭐ Database Management

⭐ Business Intelligence

⭐ Statistical Designing

⭐ ETL & Data Cleaning

⭐ Machine Learning

Featured Projects

Snowflake–S3 Automated Data Pipeline

Snowflake | SQL | AWS

A fully automated data pipeline built using AWS S3 and Snowflake, designed to ingest raw CSV files from S3, load them into Snowflake using a storage integration and pipe, transform active employee records through a dynamic table, and export the cleaned dataset back to S3 as analytics-ready files.

Project Summary

Gemini_Generated_Image_76oy6176oy6176oy.png

Country Development Clustering Analysis (KMeans & PCA)

Python | Pandas | NumPy | Scikit-learn

Built an unsupervised ML pipeline using KMeans and PCA to cluster countries into development categories based on socio-economic indicators, applying feature scaling, silhouette-based evaluation, and data-driven cluster interpretation to generate clear, actionable insights for visualization and dashboarding.

Project Overview

Gemini_Generated_Image_uzlj1zuzlj1zuzlj.png

Steel Surface Fault Classification using Machine Learning

Python | Pandas | NumPy | Scikit-learn

An end-to-end machine learning pipeline built using Python and Scikit-learn to preprocess industrial sensor data, train and tune a Random Forest model for steel surface fault classification, and export deployment-ready model artifacts for automated and scalable quality control.

Project Summary

E-Commerce Sales & Revenue Dashboard