Naga Ratna Aashishya Iruku

Detail-oriented team player with strong organizational skills. Ability to handle multiple projects simultaneously with a high degree of accuracy. To seek and maintain a full-time position that offers professional challenges utilizing interpersonal skills, excellent time management and problem-solving skills.

Comparative analysis of Quadratic boost converter with Conventional boost converter (Final Year Project), 

• Designed and implemented a quadratic boost converter power interface for a renewable energy conversion system using MATLAB and LabVIEW software.
• Compared boost and quadratic boost power interfaces to a renewable energy conversion system using MATLAB and LabVIEW software, finding that the quadratic boost converter provided 20% better output power (120 W vs. 100 W).
• Demonstrated that a quadratic boost converter provides better output power when employed as a power interface than a boost converter.

 Job Recruitment Portal (Open Lab Project)

• Developed a user login page and dashboard for a job recruiting platform using HTML, CSS, and SQL.
• Implemented a secure user authentication system using SQL to store and verify user credentials.
• Created a user-friendly and visually appealing dashboard that allows users to manage their job applications and track the status of their applications.

Movie Recommendation System

• Developed a movie recommendation system using Apache Spark to generate personalized movie recommendations based on users' browsing patterns and interests.
• Applied the ALS algorithm to a dataset of explicit feedback data, achieving high accuracy in predicting user ratings.
• Optimized the ALS algorithm for performance on Apache Spark, enabling the system to scale to millions of users and movies.

House Rent Prediction System

• Developed and implemented a machine learning model to predict house rent using recursion techniques.
• Utilized data cleaning and preparation pipeline to improve the quality and usability of a house price dataset, resulting in a 10% increase in model performance.
• Evaluated the performance of four different machine learning models on a house price dataset, using metrics such as R2 score, MSE, and RMSE. Identified the Gradient Boosting Regression (GBR) model as the best performer, with an R2 score of 0.95.