Aditya Vardhan Nelatur

Hyderabad

Summary

Self-directed Work Study Student motivated to apply education and experience in job role. Excellent listener comfortable completing various tasks to keep operations running smoothly.

Overview

Certification

Work History

Frontend & AIML Intern

Edunet Foundation

07.2023 - 09.2023

Built and deployed a linear regression model to predict employee burnout,
achieving 92% accuracy by analyzing 22,000+ records and optimizing key
features.
Performed extensive data cleaning and exploratory data analysis (EDA) to
identify patterns influencing employee burnout rates.
Utilized Python libraries such as Pandas, NumPy, and scikit-learn for data
preprocessing, feature engineering, model training, and performance evaluation.
Earned IBM SkillsBuild certification showcasing strong learning and implementation skills.

Education

B.Tech - Computer Science and Engineering

SRM University

Andhra Pradesh

06.2025

Intermediate - MPC

Excellencia Junior College

Hyderbad

01.2022

SSC - 10th Grade

Geetanjali High School

Hyderbad

01.2020

Skills

Programming languages: C/C, Python
Web development: HTML, CSS, JavaScript, ReactJS

Tools and Technologies: VS Code, Google Colab

Certification

MongoDB Certified Associate Developer – MongoDB Inc.
IBM SkillsBuild Certificate in AI & Data Analytics

Projects

Smart Expense - Expense Tracker

• Developed a React.js-based Smart Expense Tracker featuring a modern user interface and interactive Pie Chart visualizations, improving financial tracking efficiency by 50%.
• Implemented full CRUD operations using a JSON server for persistent data storage, enhancing data management efficiency by 40% and simplifying expense categorization and analysis.
• Technologies: React.js, JSON Server, Material UI, VS Code.

Deep Learning-Based Detection of Leaf Diseases in Potato Crops

• Developed a Plant Disease Detection system using deep learning and digital image processing techniques to classify diseased vs healthy leaves.
• Trained and evaluated multiple models including Sequential CNN (99.70% accuracy), ResNet50, DenseNet121, MobileNetV2, and VGG16.
• Applied image preprocsing (resizing, normalization, augmentation) and implemented transfer learning for performance comparison.
• Technologies: TensorFlow/Keras and Google Colab.

Timeline