In this presentation, I focus on supervised learning, a machine learning technique for performing predictive analytics. After introducing some vocabulary, I discuss the relationship between predictive analytics and machine learning. Next, I describe how you could use a classifier, such as a decision tree, to predict which passengers survived the sinking of the Titanic. Once the machine learning process is clear, I then talk about how Azure Machine Learning is an end-to-end data science solution. Finally, I demo an experiment using real world data from www.healthdata.gov.
My solution predicts the outcomes of patients who went through substance abuse treatment.
This demo led to a project at the Georgia Department of Behavioral Health and Developmental Disabilities. In order to reduce costs, optimize staffing, and support the budgeting process, we predicted demand for behavioral health crisis services in dozens of facilities across the state of Georgia. I led the data engineering, data visualization, and data storytelling parts of the project. I integrated data into a data warehouse from several previously siloed systems. While performing our analysis for this project, we also helped the organization improve their data governance and data science process. It was fun and rewarding!