Data Science Machine Learning

Nanda Kishore Vuppili

Willing to Relocate *****************@*****.*** Github Linkedin Portfolio

Education

Stony Brook University (State University of New York) Stony Brook, NY

M.S. in Data Science GPA: 3.89/4.0 January 2024 - December 2025

Coursework: Statistical Computing, Big Data Systems, Data Analysis, Data Structures & Algorithms, Probability

GITAM University Visakhapatnam, IND

B.Tech. in Computer Science GPA: 8.86/10.0 June 2019 - April 2023

Skills

Languages: Python, SQL, Java, R, C, HTML, CSS

Databases and Tools: Excel, Git, Github, Google Colab, Visual Studio, Docker, Snowflake, MySQL, PostgreSQL, Redshift, Oracle, MongoDB, NoSQL, PySpark, Apache Airflow, Apache Spark, Hadoop, Hive, dbt, Kafka

Cloud Platforms: Amazon AWS (S3, EC2, Lambda), Azure (Data Lake, Synapse), Google Cloud (BigQuery, Dataflow)

Machine Learning: Matplotlib, Scikit-learn, TensorFlow, Pytorch, Keras, XGBoost, NLP (BERT), Predictive modeling

General: ETL, Pipeline Optimization, Data Visualization, Data Warehousing, Statistics, Data Modeling, Predictive Analysis, A/B Testing, Agile Methodologies, APIs, KPI, Problem-Solving

Experience

GITAM University Visakhapatnam, IND

Research Scholar November 2022-April 2023

●Developed and deployed a deep learning-based sentiment analysis system for YouTube videos, achieving 80% accuracy in emotion detection by integrating CNN for facial recognition and VADER for comment analysis.

●Implemented an interactive UI enabling users to upload videos or share YouTube links for real-time analysis.

●Optimized data storage and retrieval by designing a hashing-based map table, cutting load time by 30%, and reducing redundant processing, which enhanced system performance for faster and more reliable analysis.

●Published the research findings in ”Shodhasamhita: Journal of Fundamental and Comparative Research” .

Phoenix Global Trade Solutions Visakhapatnam,IND

Full Stack Engineer Intern May 2022 – August 2022

●Data Analyst Contribution: Engineered an e-commerce dashboard using JavaScript and Tableau, boosting user engagement by 20% through real-time sales tracking.

●Pipeline Optimization: Streamlined remote shopping features using Agile methodologies, enhancing product accessibility and increasing online revenue by 40% while boosting customer retention by 25%

Projects

R Stats: Advanced Modeling and Variable Selection

●Created an R package for advanced statistical modeling, implementing linear, logistic, ridge, LASSO, and elastic net regression, supporting datasets with up to 10,000 predictors.

●Boosted accuracy by 15% via ensemble learning and bagging, using bootstrap aggregating across 100 datasets.

●Improved variable selection efficiency by 30% using pre-screening of top 50 predictors, enhancing performance .

Real-Time Uber Demand Analytics

●Built an automated ETL pipeline on GCP, reducing manual effort by 100% with monthly scheduled processing.

●Achieved 85% trip duration accuracy and 0.012 MSE in demand forecasting using BERT and LightGBM.

●Developed Looker Studio dashboards for real-time insights on demand, trip duration, and revenue trends.

Tokyo Olympics Analysis

●Streamlined data for 11,000+ athletes across 743 teams using Azure Data Factory and Databricks, optimizing storage and transformation.

●Automated Data pipelines for enriched datasets in Azure Data Lake, enabling advanced analytics with Synapse.

●Created Power BI dashboards to visualize key Olympic metrics, including the US winning 4.7% of all medals.

Certifications

●British Airways Data Science Job Simulation on Forage; IBM Data Analysis with Python

Contact this candidate