With the development of learning analytics and predictive technology has come an opportunity, or the sense of an opportunity, to predict the behaviour of individuals – be that potential criminals, the habits of shoppers or, indeed, students.
Ever since the University of London International Programmes was established, way back in 1858, we have had an open access mission for students. Wide provision and flexible modes of study inevitably mean we will have higher attrition rates compared to some campus-based universities. In addition, understanding and supporting the student life-cycle of a large and globally scattered population can be challenging (our 54,000 students study in 180 countries).
Therefore, aside from the ‘bottom-line’ consideration of decreasing the number of students leaving our programmes, we felt that using such technologies could help us understand more about how our students engage with us throughout their studies.
Wide provision and flexible modes of study inevitably mean we will have higher attrition rates compared to some campus-based universities
We think that pulling together a variety of data sources into one system will give us insight into when and why students engage (or not), or are particularly happy (or not), and can help us improve in areas like student support, VLE provision, or assessment.
We opted for a two-phase approach to learner analytics. Phase 1 identifies the students who we think might be at risk of disengaging from our programmes by using the Bloom Thrive pilot. Phase 2 is to develop the student support and engagement practices with which we might intervene using analytic outputs.
Initial tests, using historic data and a small number of indicators usually analysed by Bloom Thrive, identified a slightly higher rate of student attrition than our general level. We’re now closer to being able to predict future outcomes for our students and we think the live triggers and data of the system will add depth to these, allowing more sophisticated support and intervention.