Leveraging Performance and Feedback-Seeking Indicators from a Digital Learning Platform for Early Prediction of Students' Learning Outcomes

Background: Students' tendencies to seek feedback are associated with improved learning. Yet, how soon this association becomes robust enough to make predictions about learning is not fully understood. Such knowledge has strong implications for early identification of students at-risk for underachievement via digital learning platforms. Objectives: We sought to understand how early in the academic year students' end-of-year learning outcomes could be predicted by their performance and feedback-seeking behaviours within a digital learning platform. We analysed data collected at different time points in the academic year and across different cohorts of students within the context of high school advanced placement (AP) Statistics courses. Methods: High school students enrolled in AP Statistics spanning three academic years between 2017 and 2020 (N = 726; M[subscript age] = 16.72 years) completed 3 or 4 homework assignments, each 2 and 3 months apart. Results and conclusions: Across the three cohorts, and even as early as the first assignment, a model consisting of demographic variables (gender, race/ethnicity, parental education), assignment performance, and interaction with the digital score report explained significant variation in students' final course grades (R[superscript 2] = 0.314-0.412) and AP exam scores (? = 0.583-0.689). Students' assignment performance was positively associated with end-of-year learning outcomes. Students who more frequently checked their digital score reports tended to receive better learning outcomes, though not consistently across cohorts. Implications: These findings further an understanding of how students' early performance and feedback-seeking behaviours within a digital learning platform predict end-of-year learning outcomes.