This paper presents a new approach to automatically detect- ing lower-performing or “at-risk” students on computer programming modules in an undergraduate University degree course. Using histori- cal data from previous student cohorts we built a predictive model using logged interactions between students and online resources, as well as stu- dents’ progress in programming laboratory work. Predictions were cal- culated each week during a 12-week semester. Course lecturers received student lists ranked by their probability of failing the next computer- based laboratory exam. At-risk students were targeted and offered assis- tance during laboratory sessions by the lecturer and laboratory tutors. When we group students into two cohorts depending on whether they failed or passed their first laboratory exam, the average margin of im- provement on the second laboratory exam between the higher and lower- performing students was four times higher when our predictions were run and subsequent laboratory support targeted at these students, compared to students from the year our model was trained on.