BHAVESH SAPKALE

Tools Used: Python, Power BI, Tableau, SQL

Project Overview:
This project focused on performing a complete ETL (Extract-Transform-Load) and analytical pipeline on Amazon e-commerce sales data. The goal was to analyze sales trends and extract business intelligence insights to support strategic sales decision-making.

Key Contributions:

Performed end-to-end ETL process to clean, transform, and prepare Amazon sales data for visualization and reporting

Analyzed month-wise, year-wise, and combined yearly-monthly sales trends to identify revenue fluctuations and seasonal demand

Identified key performance metrics (KPIs) such as sales volume, top-performing months, regions, and product categories

Created interactive dashboards using Power BI/Tableau to visually communicate trends and relationships between attributes

Followed best practices including PEP8 standards, modular and maintainable code, and GitHub version control with a detailed README and architecture documentation

Contributed to high-level and low-level design documentation, wireframes, and a detailed final report as part of the professional project submission

Outcome:
Delivered a full-stack BI solution demonstrating the ability to work with large-scale retail data, communicate findings effectively, and contribute to data-driven decision-making within an e-commerce context.

Tools Used: Python, Pandas, Seaborn, Matplotlib, Jupyter Notebook

Project Overview:
This project involved exploring and analyzing a large restaurant dataset to extract insights about food delivery trends, popular cuisines, rating patterns, and city-wise service distributions. The goal was to uncover actionable insights that could inform strategic decisions in the restaurant industry.

Key Contributions:

Analyzed over 9,000 restaurant records to identify key patterns in customer ratings, delivery availability, and pricing categories

Cleaned and transformed raw data by handling missing values and formatting inconsistencies to ensure analysis-ready structure

Created informative visualizations (heatmaps, bar charts, count plots) to uncover trends in cuisine popularity, location-based preferences, and service types

Highlighted how certain cities preferred specific cuisines and how pricing impacted customer ratings

Delivered a comprehensive Jupyter Notebook with over 170 structured code cells, combining EDA, visual storytelling, and interpretation

Outcome:
The project showcased my ability to work with real-world datasets, apply Python-based analysis, and draw insights that bridge data and business relevance. This internship solidified my data wrangling, visualization, and storytelling skills.