Automated Prediction of Novice Programmer Performance Using Programming Trajectories

Rubio, Miguel A.

Online programming courses have become widely available and host thousands of learners every year. In these courses, participants must solve programming exercises by submitting partial solutions and checking the outcome. The sequence of partial solutions submitted by a student constitutes the programming trajectory followed by the student. In our work, we define a supervised machine learning algorithm that takes as input these programming trajectories and predicts whether a student will successfully complete the next exercise. We have validated our model with two different datasets: the first one is a set of problems from the online learning platform Robomission with over one hundred thousand exercises submitted. The second one comprises one hundred thousand exercises submitted to the Hour of Code challenge. The results obtained indicate that our model can accurately predict the future performance of the students. This work provides not only a new method to represent students’ programming trajectories but also an efficient approach to predict the students’ future performance. Furthermore, the information provided by the model can be used to select the students that would benefit from an intervention.