Komal Poojari

Data Science Graduate

Mumbai 0+ yrs exp 81 · Excellent

About

2026 B.Tech Data Science graduate with hands-on experience in Python, SQL, Pandas, Excel, data cleaning, transformation, and data analysis. Built Python-based data workflows involving API data extraction, JSON processing, ETL, and SQL databases. Strong analytical problem-solving, attention to detail, communication, and interest in Data Engineering.

Skills & Expertise (39)

Python Advanced

8.2/10

0.3

Years Exp

SQL Advanced

8.0/10

0.3

Years Exp

Pandas Advanced

8.0/10

0.3

Years Exp

Data Cleaning Advanced

8.0/10

0.3

Years Exp

Data Visualization Advanced

8.0/10

0.3

Years Exp

Power BI Advanced

8.0/10

0.3

Years Exp

Natural Language Processing Intermediate

7.0/10

0.3

Years Exp

Business Communication Intermediate

7.0/10

0.3

Years Exp

Data Storytelling Intermediate

7.0/10

0.3

Years Exp

Embeddings Attention to Detail Analytical Thinking Business Problem Solving Teamwork NumPy Data Transformation A/B testing ANOVA Chi-square T-test Confidence Intervals P-values Hypothesis Testing Descriptive Statistics JSON Retrieval-Augmented Generation Large Language Models Generative AI Deep Learning Exploratory data analysis Random Forest Classification Regression scikit-learn ETL REST APIs Microsoft Excel Data Processing SQLite

Work Experience

AI Intern

Edunet Foundation

Jan 2026 - Apr 2026

Analyzed 25,000+ business records using Python, SQL, and Excel to generate actionable business insights. Cleaned, validated, and transformed business datasets to improve reporting accuracy and maintain data consistency. Automated repetitive data preparation and reporting tasks using Python and Excel, reducing manual reporting effort. Built interactive Power BI dashboards for KPI tracking and management reporting and presented findings to cross-functional stakeholders. Worked with large structured datasets and communicated data-driven findings through dashboards and reports. Built a machine learning system using Logistic Regression and Random Forest to predict loan default risk. Performed data cleaning, EDA, feature engineering, and model evaluation on 32,000+ loan records. Achieved 93.1% accuracy using Random Forest and developed an interactive Power BI dashboard for business insights.