Improving Retention Performance Prediction with Prerequisite Skill Features

This paper describes our experiment and analysis of utilizing prerequisite skill features to improve the predicting of student retention performance. There are two aspects that make this paper interesting. First, instead of focusing on short-team performance, we investigated the student retention performance after a delay of 7 days. We explored several prerequisite skill features that can be captured in an intelligent tutoring system; in our particular case, these prerequisite skill features were acquired from Common Core standard skills and student data while working on these skills. We showed that some of these features have encouraging predictive power. Our analysis confirmed the value of prerequisite skill features in predicting retention performance, the prediction results showed an improvement from an R2 of 0.182 with a baseline feature set to an R2 value of 0.192.