Harshada Pujari - Data Analyst Portfolio

About Me

Hi, I'm Harshada! I am a detail-oriented Data Science professional currently pursuing a Master's in Business Analytics (MSBA) from Santa Clara University. I have a background in developing machine learning models, performing statistical analysis, and uncovering actionable insights from complex datasets.

Work Experience

Data Analyst (Practicum) | Pluto7

Collaborated with cross-functional teams to gather business requirements and analyze data from 14,000+ consumer reviews of skincare products.
Implemented NLP models using Python (NLTK, Open AI APIs) for sentiment analysis, providing actionable insights for improving customer satisfaction.
Developed a ranking system based on metrics like performance, sustainability, and packaging.

ETL Developer | Capgemini Technology Services

Developed data pipelines and ETL workflows to process order and product data for analysis, ensuring data integrity.
Built SQL and Linux shell scripts for modeling and analyzing data, and created Tableau visuals for business decision-making.
Increased ticketing reporting efficiency by 50% through the automation of data processes using VB scripts.

Portfolio Projects

Koolboks Pricing and Repossessions

Tools: Python - Pandas, Numpy, Excel

Developed a Random Forest classifier to predict client default risk.
Identified KPIs affecting repayments.
Reduced default rates by 10% for 2000+ clients.

Segmentation and Lifetime Value Analysis of Franchises for Jibu

Tools: R, Excel

Performed RFM analysis and K-means clustering to segment franchises, boosting performance by 10% through targeted strategies.
Built a CLV model to inform marketing and resource allocation decisions, improving franchise insights.
Achieved R² of 86% using regression to predict franchise performance, supporting strategic growth initiatives.

Diamond Price Prediction

Tools: Python - Pandas, Numpy

Built predictive models to forecast diamond prices using Python.
Achieved an R² of 99.16% in price predictions.

Additional Projects

R-Programming: Effect of Education on Savings - Analyzed how education impacts savings behavior.
R-Programming: Linear Optimization of Support Staffing at Tesla Call Center - Solved staffing optimization issues using R programming.
Python-ML: Netflix TV Shows and Movies Analysis - Performed a machine learning analysis on Netflix datasets.