SAI NISCHAY KODATI

Cloud Engineer Intern

Ctrl-S

04.2020 - 07.2020

Spent majority of internship learning AWS and Azure, dedicating about 80% of time to completing 10 courses, attending 5 workshops, and earning 3 certifications
Contributed to organization by processing average of 50 tickets per day, resulting in 20% reduction in ticket resolution time during tenure
Implemented seamless integration between PostgreSQL databases and workspaces, optimizing data accessibility and improving team collaboration efficiency by 40%
ACADEMIC PROJECTS
Major project on Brain-Computer Interface, achieved remarkable 90% accuracy in detecting human emotions through analysis of brain waves, demonstrating significant advancements in emotional state recognition technology
Collected Brain waves data using EEG headset, labelling data and preparing it for training and testing
Obtained excellent 95% accuracy in identifying patterns within dataset after training the model with 50 important features retrieved from labeled data, highlighting efficacy of feature extraction and model training approach
Attained accuracy score of 92% and mean squared error (MSE) of 0.05 after testing model using testing dataset
These results demonstrate model's strong performance in correctly predicting outcomes
Customer Retention Analysis of a Bank
Explored existing bank data to successfully predict attrition with accuracy rate of 87%, and additionally, identified and predicted several minor factors, each contributing to improved model performance and overall business insights
Conducted predictive analysis utilizing Logistic Regression (92% accuracy) and Decision Trees (0.12 MAE), along with Random Forest (Top 3 feature importance) and Linear Regression (R-squared: 0.85)
Evaluated model performance against split testing dataset, achieving impressive 91% accuracy and F1-score of 0.89, highlighting its robustness and reliability
Accuracy ranged from 88% (Logistic Regression) to 95% (Random Forest) for fraud job posting prediction, with regression models consistently achieving MSE below 0.1, highlighting their precision and reliability
Prediction of Fraud Job Posting
Analyzed data from job posting websites (Glassdoor, Indeed, LinkedIn), processing 5,000+ job postings to reveal industry trends, job market insights, and salary benchmarks across roles and locations
Cleaned and preprocessed dataset, removing 300 duplicate entries, filling in missing values for 150 records, and transforming data into standardized format, resulting in clean and comprehensive dataset for analysis
Utilized NLP for text preprocessing, including tokenization, stemming, and stop-word removal, reducing text data dimensionality by 30%
Improved NLP tasks' efficiency and boosted sentiment analysis accuracy by 10%
Created and implemented Python regression models to predict fraudulent job postings, reaching excellent 92% accuracy rate and a Mean Squared Error (MSE) of 0.08, indicating models' efficacy in spotting fake job listings based on studied data.

Overview

Work History

Data Scientist Intern

Cloud Engineer Intern

Education

Master of Science - Data Analytics Engineering

Bachelor of Engineering - Electronics and Communication

Skills

Timeline

Data Scientist Intern

Cloud Engineer Intern

Master of Science - Data Analytics Engineering

Bachelor of Engineering - Electronics and Communication

Similar Profiles

Ramesh KukkapallyRamesh Kukkapally

Ava SchlottmanAva Schlottman

Aslam K. BashaAslam K. Basha

Allison DavidAllison David

Nehemie KabaseleNehemie Kabasele