Course Description
In contrast to the statistical modeling course which focuses on understanding the influence of variables on outcomes, this course will focus on predicting individual health outcomes using modern automated model development algorithms. By the end of this course, students will be able to create predictive analytics using popular machine learning packages in R and Python.
In this course, students will learn to apply modern statistical/machine learning techniques to answer questions specific to the healthcare industry. The bulk of the semester will be spent on supervised learning techniques for regression and classification. The last few weeks will touch on unsupervised learning techniques for uncovering previously unknown patterns in data. This hybrid course will have both online and in-class workshop components.
Learner Outcomes
Upon completion of the course, students will:- Understand the appropriate applications for supervised and unsupervised learning methods.
- Be able to train regression and classification models.
- Assess the predictive ability of fitted models.
- Collaborate and share scripts with other students.
- Describe methods and communicate findings to general audiences.
Prerequisites
GEO5090 - Introduction to Programming for GIS/Remote Sensing or equivalent experienceDuration
30 Hours | 5 Days or 10 Nights*Academic Unit eligibility to be determined by college/university in which you are enrolled in a degree seeking program.