Rohan Nagineni profile picture

Hello, I'm

Rohan Nagineni

CS Major @ UT Austin

My LinkedIn profile My Github profile
Arrow icon

Get To Know More

About Me

Profile picture
Education icon

Education

B.S. in Computer Science
University of Texas at Austin

Experience icon

Coursework

Machine Learning, Web Applications, OOP, Data Structures, Operating Systems, etc.

I'm a Computer Science major at The University of Texas at Austin with a passion for software engineering. Through personal projects and my work experience, I've gained hands-on experience in web development, machine learning, and data analysis. I’ve worked on building real-time command interfaces for rocket missions, done extensive application testing for a medical startup, and developed platforms for movie reviews with AI insights as well as credit card fraud detection using various machine learning and deep learning models. I'm always super excited to contribute to innovative solutions and collaborate on impactful projects.

Arrow icon

Explore My

Experience

Project 1

Texas Rocket Engineering Lab

Austin, TX
Sep 2023 - May 2024
Description
  • Developed a React and Spring Boot web platform for users to explore upcoming movies and manage watchlists.
  • Enhanced application by utilizing Bootstrap for a responsive UI to display movie trailers, posters, and backdrops.
  • Implemented features for user-generated content, including reviews and watchlists, stored using MongoDB Atlas.
  • Developed REST API with Spring Boot for robust UI-data interactions, boosting data retrieval efficiency by 20%.
  • Integrated neural network from Movie Data Analysis project, enriching user experience with data-driven insights.
  • Deployed the application on AWS using EC2 for scalable deployment and efficient data management.
Project 1

iMEDRIX

Milpitas, CA
Jun 2023 - Aug 2023
Description
  • Developed a Python script to scrape and analyze over 1,000,000 movie data points from the TMDB API.
  • Implemented sentiment analysis using the VADER library on movie reviews to quantify sentiment scores.
  • Engineered features and normalized data, including budget, and popularity metrics to enhance model accuracy.
  • Created and optimized neural network hyperparameters using Keras and Grid Search, achieving an 8% boost in accuracy with a final test accuracy of 79%, demonstrating strong predictive capabilities of movie success.
Arrow icon

Browse My Recent

Projects

Project 1

Movie Watch-list and Review Website

Description
  • Developed a React and Spring Boot web platform for users to explore upcoming movies and manage watchlists.
  • Enhanced application by utilizing Bootstrap for a responsive UI to display movie trailers, posters, and backdrops.
  • Implemented features for user-generated content, including reviews and watchlists, stored using MongoDB Atlas.
  • Developed REST API with Spring Boot for robust UI-data interactions, boosting data retrieval efficiency by 20%.
  • Integrated neural network from Movie Data Analysis project, enriching user experience with data-driven insights.
  • Deployed the application on AWS using EC2 for scalable deployment and efficient data management.
Project 2

Movie Data Analysis /Success Prediction

Description
  • Developed a Python script to scrape and analyze over 1,000,000 movie data points from the TMDB API.
  • Implemented sentiment analysis using the VADER library on movie reviews to quantify sentiment scores.
  • Engineered features and normalized data, including budget, and popularity metrics to enhance model accuracy.
  • Created and optimized neural network hyperparameters using Keras and Grid Search, achieving an 8% boost in accuracy with a final test accuracy of 79%, demonstrating strong predictive capabilities of movie success.
Project 2

Credit Card Fraud Detection

Description
  • Engineered, balanced, and normalized features in a dataset of 280,000+ credit card transactions.
  • Partitioned data into training, validation, and testing sets to strategically evaluate model performance metrics.
  • Developed and tested multiple machine learning models including logistic regression, decision trees, and GBCs.
  • Utilized Tensorflow to create deep learning models like neural networks for more effective fraud detection.
  • Achieved notable metrics with the best model, the Gradient Boosting Classifier, reaching a precision of 95% and a recall of 86% on the test data set, outperforming unoptimized models by over 15% with a resulting f1-score of 0.90.
Arrow icon

Take A Look At My

Skills

Languages

Java

Python

C/C++

Javascript

Typescript

SQL

Clojure

Frameworks

Spring Boot

Node.js

Vue.js

Flask

Google Test

JUnit

Express.js

Tools

AWS

Git

Docker

MongoDB

Jira

VSCode

Unix

Libraries

React

Scikit-learn

Tensorflow

pandas

NumPy

Matplotlib

Beautiful Soup

Arrow icon

Get in Touch

Contact Me

rohannagineni@utexas.edu

LinkedIn icon

LinkedIn