Automating Business Processes - Customer Journey: Fully automated process of gathering, cleaning, assigning, and creating sales opportunities for eligible leads - Email Marketing Stats: Aggregating metrics for each email campaign (delivery rates, open rates, click rates, sales, etc.) - Email Marketing Segmentation: Automatically generate distribution lists based on past purchase/behavior - Pricing Recommendations: Automated dynamic price recommendations based on demand, days until the game, and secondary pricesPredictive Modeling (Using Python and R) - Season Ticket Holder Retention - Ticket Sales Projections - Optimal Price Projections - Lead Scoring

Maintain Data Warehouse and manage data collection processes - Extract data from various sources (outside databases, web scrapping, API calls, etc.) - Transform, normalize, and clean data - Load data into data warehouse via Python and AWSGathered, cleaned, explored, and fit predictive models on large data sets - Presented findings as a story to both technical and non-technical audiences via Tableau and other presentation tools

- Assist students with code and concepts on projects and labs- Lead review lectures- Provide timely feedback on assignments

Gathered, cleaned, explored, and fit machine learning models on large datasets using Python. Presented findings as a story to both technical and non-technical audiences. Projects:-Predict home prices based on several features of houses in Ames, Iowa.Technologies used: Python, Docker, SKLearn, and Pandas https://github.com/eprentice30/DSI_housing-Madelon Dataset: Reduced 500 features to 8 relevant features with 89.6% accuracyTechnologies used: Python , AWS EC2 instance, SKlearn, and Pandashttps://github.com/eprentice30/dsi_Madelon- Query into the Wikipedia API and collect all the contents of pages within a specified category. Then used Latent Semantic Search to find top 5 related articles for a given search word.Technologies used: MongoDB, AWS EC2 instance, Requests, SKLearn, and Pandashttps://github.com/eprentice30/semantic_search- HR Analytics: Predict employee attrition, quality, and lifecycle. Obtained 90% acccuracy for employee attrition and an R^2 = .89 for employee's years at the company. Developed a strategy to combat attrition in the hopes of finding significant savingsTechnologies used: Lifelines, SKLearn, ML-Insights (Reliability Plots), TensorFlow, and Pandashttps://www.kaggle.com/eprentice30/saving-ibm-a-bunch-of-money