Lightning Round Session: Creating a Culture of Data-Informed Decision-Making

This lightning round will pack as much information into one session as possible. Hear succinct, engaging presentations on a variety of topics. Each will be 10 minutes long, with a Q&A at the end of the session.

Lightning Round 1: Course Design as Learning Analytics Variable—and Intervention

By focusing on digital tool usage as a proxy for student engagement and an expression of instructor pedagogy, this presentation will focus on how LMS course design has been conceptualized as a plausible learning analytics variable and realized as one of the most scalable, transformative forms of intervention any institution can pursue.

Outcomes: Better understand how course design can be a learning analytics variable worthy of further study * Obtain practical examples that demonstrate these developments in an institutional context * Be able to assess potential applications of learning analytics for your institution

Presenters: John Fritz, Thomas Penniston (University of Maryland, Baltimore County)

Lightning Round 2: Increase Faculty Adoption of Learning Analytics in Teaching and Learning

Learning analytics promotes faculty reflective practice in teaching and learning. We will discuss various institutional efforts to support faculty adoption of learning analytics in the pursuit of excellence in teaching and explore specific programs, services, and communication strategies to increase faculty adoption in your own courses to help students.

Outcomes: Explore various learning analytics resources for faculty in teaching and learning * Identify key elements and players in faculty adoption of learning analytics * Develop communication strategies to promote faculty adoption of learning analytics

Presenters: Sean DeMonner (University of Michigan–Ann Arbor), Jason Kaetzel (Indiana University, Bloomington), Jae-Eun Russell (The University of Iowa)

Lightning Round 3: Predictive Models for Students: Ethical and Practical Considerations

Machine learning algorithms are capable of accurately predicting student outcomes. However, ethical and practical decisions must be made about what variables should be included in these models. In this session, we will compare the accuracy and impact of predictive models using different feature sets and explore how institutions might best leverage these predictions.

Outcomes: Understand the differences in accuracy across the semester of predictive models using different feature sets and the different ways models can be "wrong" * Identify the potential benefits and consequences of including certain features * Explore when and how predictions might best be shared with students

Presenters: Anna Smith (The University of Iowa)