The Learning Analytics Graduate Academic Certificate
As increasing amounts of data are collected in learning environments, analysts are
needed who can collect, interpret, and analyze data to improve learning outcomes and
processes. Individuals who qualify for these positions must be able to apply not only
technical and analytical skills, but also an understanding of learning theories and
instructional design. This unique combination of skills and knowledge is needed for
developing and implementing effective learning solutions.
Building on the Master of Science degree in Learning Technologies (Learning Analytics
concentration), the 4-course graduate academic certificate (GAC) in Learning Analytics
prepares professionals to apply data-driven techniques to understand and improve learning
processes both in education and in business. The Learning Analytics certificate provides
students with scaffolded skill development as they apply learning analytics algorithms
and techniques to real-world educational and training datasets and case studies. Learning
is deepened through hands-on activities that support learners in building skills while
analyzing real-world, contextualized datasets and summarizing important variables
and model predictions.
Individuals who complete the LA GAC will:
A total of 12 hours, or 4 courses, is needed to complete the certificate:
Provides an introduction to learning analytics with a focus on Python programming and Exploratory Data Analysis (EDA) in educational contexts. Tailored for students interested in applying data-driven techniques to understand and improve learning processes. Learn the fundamentals of Python programming, including data manipulation and visualization, while working with real-world education datasets. Through hands-on projects, explore patterns in student performance, engagement, and learning behaviors, gaining practical skills relevant to educational research and decision-making.
Explores predictive modeling techniques in the context of learning analytics, focusing on how machine learning can be applied to educational data to inform decision-making and improve student learning outcomes. Emphasizes the unique challenges and opportunities in analyzing student performance, engagement, and learning behaviors. Learn and apply various machine learning algorithms and techniques, including multiple regression, logistic regression, decision trees, and random forests, to real-world education datasets. Through hands-on exercises and case studies, develop the skills to build, interpret, and evaluate predictive models tailored to educational research and policy.
Prerequisite(s): LTEC 5601.
Capstone course focuses on the design, development, and deployment of interactive dashboards for learning analytics. Integrate concepts from previous courses to create data-driven visualizations that address real-world educational challenges. Using various Python frameworks, build dynamic dashboards that communicate insights from Exploratory Data Analysis (EDA), predictive models, and text analysis in meaningful ways for educators, administrators, and policymakers. Equips students with the technical and design skills necessary to translate complex learning analytics into actionable insights through interactive applications.