Previous results showed that Automated Reassessment and Relearning System (ARRS) helps improving student learning. In this study, we are trying to answer the question: Can ARRS also help assessing student long-term knowledge? In turns out the answer is "yes", this ARRS data help you better predict test scores approximate 6 months later. That is if you give kids a skill builder versus a skill builder PLUS the ARRS test one week later, the additional information that is the ARRS tests helps you do a better job in predicting the post test 6 months later.
Wang, Y. & Heffernan, N. (2014). The Effect of Automatic Reassessment and Relearning on Assessing Student Long-term Knowledge in Mathematics. In Stefan Trausan-Matu, et al. (Eds) International Conference on Intelligent Tutoring 2014. pp 490-495. (The data for this paper is here.)