Data Science in GCP
Databases and SQL
Galvanize Data Science Immersive
B.S. Public Health, University of Toledo
International Lifestyle Clothing and Accessories Retailer
Built a general-purpose recommendation engine for that is used for real-time recommendations on the customers’ production website. The engine utilizes random forests to identify the propensity to buy in customers to boost sales. It was implemented in BigQuery and Spark. Developed segmentation models to target customers with specific offers.
Regional Car Wash Chain
Markdown Optimization and Churn Prediction
Analyzed data for a large car wash chain to determine the effectiveness of their markdown strategy. Built a customer churn model using random forests to determine the likelihood of churn prior to subscription expiration, as well as targeting customers at risk for non-renewal of their subscription.
Python data stack: scikit-learn, pandas, numpy, Jupyter, others
Databases: PostgreSQL, Teradata, MySQL
Machine Learning: supervised learning, unsupervised learning
Google Cloud Platform: BigTable, BigQuery, Dataproc