Machine Learning Data Science

Resume

Rishith Reddy Bandaru

Email : ************.*******@*****.*** Mobile : +1-704-***-****

Education

Master of Science in Data Science and Business Analytics December 2023 University of North Carolina at Charlotte 3.97/4.0 GPA

Bachelor of Technology in Information Technology May 2022 Sreenidhi Institute of Science and technology 3.5/4.0 GPA

Hyderabad, India

Technical Skills

Programming Languages: Python, Java, R

Operating Systems: Linux (Ubuntu, CentOS), Windows

Infrastructure Tools: AWS (S3, Lambda, EC2, SageMaker, CloudWatch), GCP(BigQuery), Azure

Database Technologies: SQL, Oracle, Snowflake

Data Analysis/Visualization Tools: Tableau, Streamlit, Matplotlib

Version Control: Git/GitHub

Web Technologies: HTML, CSS, JavaScript.

Machine Learning: Large Language Models (LLMs), Natural Language Processing (NLP), Linear Regression, Logistic Regression, KNN, PCA, Decision Tree, K-Means, Hierarchical Clustering.

Work Experience:

Research Assistant - Active Aging Insights August 2023 – December 2023

University of North Carolina at Charlotte, Charlotte, NC

Employed AWS for data storage and processing, facilitating efficient analysis of smart variable data.

Generated comprehensive weekly reports summarizing key findings and driving project progress.

Performed statistical modeling in Python for data manipulation, data mining and data validation using

libraries such as Pandas, Scikit learn, matplotlip and Numpy, Seaborn.

Utilized Python and Pandas to clean, transform, and prepare smart wearables datasets for rigorous statistical analysis.

Analyzed search ranking and relevance requirements, identifying key issues and opportunities for improvement.

Conducted ANOVA testing to determine the significant effects of demographic factors on research outcomes within smart variable data, driving deeper understanding of research questions.

Leveraged machine learning techniques to build and deploy predictive models for classifying activity types based on smart variable data, enhancing research capabilities.

Research Assistant - CO2 Emission in USA tableau Dashboard

University of North Carolina at Charlotte, Charlotte, NC. January 2023 – May 2023

Developed a Tableau dashboard showcasing state-wise CO2 emissions in the USA from coal, oil, and gas.

Integrated Tableau with Snowflake for data extraction and seamless connectivity.

Created different visuals like Symbol Map, Bar charts, Treemap and Line chart.

Published the interactive dashboard, demonstrating proficiency in both data engineering and visualization.

Dashboard Link: Car CO2 Emission in USA tableau Dashboard

Research Assistant - HandBook Web Application

University of North Carolina at Charlotte, Charlotte, NC. September 2022 – December 2022

Developed a user-friendly data visualization and machine learning model selection web application using Python and Streamlit, simplifying data analysis for non-coders.

Automated model selection based on data characteristics, enhancing decision-making, and streamlining the process for users, resulting in increased efficiency in data-driven tasks.

Tech-Stack- Python and Streamlit.

Link: https://handbook.streamlit.app/

Data Science and Analytics Intern

Spark Foundation, Hyderabad, India September 2021 – October 2021

Analyzed student study time data and deployed predictive models using supervised machine learning techniques (linear regression, decision trees); successfully forecasted exam scores with an average accuracy of 85%, enabling targeted interventions to enhance academic outcomes.

Conducted unsupervised machine learning analysis on the Iris dataset using the K-means algorithm to identify clusters and visualize results.

Overcame challenges such as handling missing data and selecting appropriate algorithms to achieve high accuracy in predictive models and clustering analysis.

Utilized Tableau for creating insightful data visualizations, aiding in the communication of research findings.

Data Science Intern

Unschool, Hyderabad, India August 2020 – August 2020

Developed a predictive model to detect fraudulent credit card transactions using logistic regression.

Utilized a dataset of credit card transactions, focusing on identifying patterns indicative of fraud.

Applied data preprocessing techniques, including handling missing values, normalization, and feature engineering.

Achieved high accuracy in distinguishing fraudulent transactions from legitimate ones.

Employed Python libraries such as Pandas, Scikit-learn, and Matplotlib for data analysis and model building.

Visualized results and performance metrics using Power BI to effectively communicate findings.

Course Projects:

End-to-End Question Answering System

Developed an AI-powered question answering system using BERT for understanding and answering user queries.

Fine-tuned pre-trained models and implemented the system in Python using TensorFlow.

Evaluated performance with standard metrics to ensure high accuracy and reliability.

AWS-Based Predictive Analysis Project

Collaborated on an AWS-based predictive analysis project for real-time machine failure prediction.

Utilized Amazon S3, Lambda, EC2, SageMaker, CloudWatch, and SES for data storage, processing, and monitoring.

Assisted in integrating CloudWatch for real-time alerts and SES for automated notifications.

Credit Card Fraud Detection

Developed a predictive model to detect fraudulent credit card transactions using logistic regression.

Utilized a dataset of credit card transactions, focusing on identifying patterns indicative of fraud.

Applied data preprocessing techniques, including handling missing values, normalization, and feature engineering.

Achieved high accuracy in distinguishing fraudulent transactions from legitimate ones.

Employed Python libraries such as Pandas, Scikit-learn, and Matplotlib for data analysis and model building.

Visualized results and performance metrics using Power BI to effectively communicate findings.

Analyzing Shakespeare Texts

Developed a web application using Streamlit, Python, and various libraries for analyzing Shakespeare's plays.

Included a word cloud generator, a bar chart showing word frequency, and a sentiment analysis tool.

Tech-Stack: Streamlit, Python, NLTK, Matplotlib, Pandas, Altair

Link: https://rishith2000-streamlit-word-bar-text-analysis-ps0j9n.streamlit.app/

Heart Disease Prediction

Developed a system predicting the likelihood of patients getting heart disease using 15 medical parameters.

Enabled significant knowledge about relationships between medical factors and patterns related to heart disease.

Tech Stack - Python, Data Science.

Crop Recommendation System

Created a crop recommendation system predicting suitable crops based on user-provided soil data.

Tech Stack - Python, Machine Learning

Certifications

Passed LinkedIn Skill Assessment - Python

Passed LinkedIn Skill Assessment- SQL

Passed LinkedIn Skill Assessment- GCP

Contact this candidate