OU Analyse

A list of such students is communicated weekly to the module and Student Support teams to help them consider appropriate support. The overall objective is to significantly improve the retention of OU students. This is 'research-led' as the project builds on previous experience from the Jisc funded Retain in 2010/2011 and the joint OU-Microsoft Research Cambridge project in 2012/2013.

The work is innovative in that it is applying machine learning techniques to two types of data: student demographic data and dynamic data represented by their VLE activities. Records of previous presentations are used to build and validate predictive models, which are then applied to the data of the presentation currently running.


Hlosta, Martin, Papathoma, Tina, Herodotou, Christothea, Explaining Errors in Predictions of At-Risk Students in Distance Learning Education

Herodotou, Christothea, Boroowa, Avinash, Hlosta, Martin, Rienties, Bart, What do distance learning students seek from student analytics?

Hlosta, Martin, Bayer, Vaclav, Zdrahal, Zdenek, Mini Survival Kit: Prediction based recommender to help students escape their critical situation in online courses

Hlosta, Martin, Zdrahal, Zdenek, Bayer, Vaclav, Herodotou, Christothea, Why Predictions of At-Risk Students Are Not 100% Accurate? Showing Patterns in False Positive and False Negative Predictions

Herodotou, Christothea, Rienties, Bart, Hlosta, Martin, Boroowa, Avinash, Mangafa, Chrysoula, Zdrahal, Zdenek, The scalable implementation of predictive learning analytics at a distance learning university: Insights from a longitudinal case study


Jakub Kuzilek Martin Hlosta Drahomira Herrmannova Zdenek Zdrahal


ActiveVisit Website