Peeyusha Patki

B.Tech AI & Data Science student · Data Entry / Data Organization

Kalyan, Maharashtra, India

@peeyusha_patki

LinkedIn GitHub

0 followers

🎓 B.Tech, Artificial Intelligence & Data Science at K. J. Somaiya Institute of Technology · Graduating 2028

Follow Message

About

Third-year B.Tech student in Artificial Intelligence & Data Science with practical experience collecting, cleaning, and organizing large datasets in Excel, Python, Databricks, and PySpark. Known for accurate, deadline-driven data handling and coordination through student committee work.

Experience

Data/AI Intern

TaskLanceAI

Aug 2026 – Sep 2026

Standardized inconsistent city names in e-commerce order records using normalization, reference mappings and fuzzy matching in PySpark. Worked with raw, cleaned and final data layers (Bronze, Silver and Gold) in Databricks to keep records consistent and traceable.
Data Collection and Organization

Family Business (Ayurvedic Publishing)

Jun 2025 – —

Collected and compiled more than 3,000 records of practicing Ayurvedic (BAMS) doctors and students from public web sources for an outreach campaign. Cleaned the data in Microsoft Excel by removing duplicates, standardizing names, phone numbers and locations, and flagging incomplete or inconsistent entries. Imported the final list into Google Contacts for WhatsApp broadcast campaigns, and improved accuracy and turnaround time across repeat campaigns.

Education

B.Tech

K. J. Somaiya Institute of Technology

Artificial Intelligence and Data Science · 2024 – 2028
High School

Narayana Junior College

2024
Secondary

Smt. K. C. Gandhi English School

2022

Skills

1 to 2 years

Data Cleaning Data Collection Data Organization

<3 months

SQL Python Pandas PySpark

Tools / apps / platforms

1 to 2 years

Microsoft Excel

<3 months

Canva Databricks

Languages

Native / Bilingual

Marathi Speak

Fluent

Hindi Speak English Speak

Projects

Drought Vulnerability Index for Indian Districts

Python

Ongoing faculty-guided project combining rainfall, El Niño and Census data for five Maharashtra districts into one dataset for correlation analysis, PCA and clustering.
Predicting Toronto Restaurant Inspection Results (DineSafe)

Python, Pandas

Rebuilt 115,899 raw rows from Toronto Open Data into 77,475 inspection records and linked older records from 2001 to 2023.
Diabetes Classification using the Canadian Community Health Survey 2022

Python, Pandas, scikit-learn

Prepared 67,079 survey responses across 255 variables, handling the survey's special answer codes variable by variable before analysis. Compared three classification models and found that the choice of predictors raised ROC-AUC from 0.774 to 0.827.

Courses & certifications

Machine Learning Foundations · AWS Educate · 2026
Introduction to Generative AI · AWS Educate · 2026

🏆 Achievements & awards

Winner, KJSIT Campus Hackathon · 2025

⚽ Extracurricular activities

Digital Cinematography & Creative Member, S4DS KJSIT Students' Chapter

Created posters and promotional content and helped organise KnowCode 3.0, a hackathon with more than 1,200 registrations; received a letter of appreciation.
Public Relations Officer, Nakshatra: Marathi Bhasha Aani Waangmay Mandal

Handled outreach, announcements and coordination between team members and external participants; received a letter of appreciation.
Trainer, AI Robotics Cell, KJSIT

Taught Arduino programming to 21 school students over a two day workshop; rated 4.52 out of 5 for teaching.

Explore the Broxer community

💬 Q&A Ask about roles, salaries and interviews — and help others. 👥 Circles Join discussions on skills, companies and industries. 📰 Feed Follow updates and insights from the community.