Welcome to my GitHub profile! I'm Derek, a Data Analytics professional passionate about harnessing the power of data to solve complex problems and drive meaningful insights. This repository showcases my projects in data analytics, machine learning, and streaming data systems.

I hold a Master of Science in Data Analytics from Northwest Missouri State University and a Bachelor of Science in Biology from the University of Wyoming. With over 8 years of professional experience spanning healthcare, biotechnology, and insurance industries, I specialize in data analysis, machine learning, and creating impactful visualizations. My work demonstrates a commitment to using data to inform decision-making and innovation.

• Programming & Tools: Python (Pandas, NumPy, Matplotlib, Seaborn, Scikit-learn), SQL, Tableau, Excel (Power Query, Pivot Tables), Power BI
• Data Analysis: Statistical Modeling, Data Cleaning, Exploratory Data Analysis (EDA), Predictive Analytics
• Machine Learning: Regression, Classification, Random Forest, K-Means Clustering, Ensemble Learning
• Streaming & Deployment: RabbitMQ, Flask, Real-time Data Processing
• Database Management: MySQL, PostgreSQL
• APIs & Web Scraping: Experience with REST APIs, BeautifulSoup, and Scrapy for data retrieval and preprocessing
• Cloud Computing: Familiarity with AWS (S3, Redshift), Google Cloud, and Azure
• Version Control: Proficient in Git/GitHub for collaborative work

Master's Capstone Project. Predicting indie game success on Steam using machine learning algorithms. This project analyzes user reviews and game metadata to identify key factors influencing game popularity and success. Includes an Overleaf report with detailed visualizations and meaningful conclusions.

Deployed a machine learning model as a web service using Flask, enabling real-time predictions via API endpoints.

A real-time auction tracking system utilizing RabbitMQ for streaming and analyzing bid data, with custom producers and consumers.

Developed an interactive NBA stat tracker using PyShiny to display player and team performance metrics. Enabled dynamic filtering and visualization of key basketball statistics for data-driven insights.

Conducted exploratory data analysis on healthcare datasets to uncover demographic and geographic trends impacting outcomes.

Feel free to explore my repositories and reach out if you have any questions or collaboration opportunities!
📧 Email: derek.graves4@outlook.com
🔗 LinkedIn: linkedin.com/in/derek-graves
🌐 GitHub: github.com/dgraves4