University learning analytics systems collate student engagement data generated when students interact with university infrastructure, such as attendance monitoring systems, virtual learning environments and library facilities.

These systems use this data to identify students with low- or no-engagement who might be at risk of lower attainment or even withdrawing from their studies. At some institutions, at-risk students may be flagged for an intervention such as an email alert, perhaps followed up by a support call.

A recent review by TASO showed that existing evidence suggests that interventions prompted by learning analytics systems can be effective but the impact is highly dependent on context and design choices. There is no comprehensive model supported by a strong evidence base to guide instructors in their work and there is little evidence from a UK setting.

What are we doing?

In order to contribute to this evidence, we have appointed Nottingham Trent University and Sheffield Hallam University to evaluate the effectiveness of interventions prompted by learning analytics through two randomised controlled trials.

The Behavioural Insights Team has been appointed as an independent evaluator for the work. The final report is due to be published early 2024.