Proceedings of the Annual Meeting of the Cognitive Science Society

The initial performance of individuals is often difficult for models of learning and retention to predict. One such modelis the predictive performance equation (PPE) a mathematical model of learning and retention that uses regularities seenin human learning to predict future performance.To generate predictions, PPEs free parameters must be calibrated to aminimum amount of historical performance data, preventing valid predictions for initial learning events.Prior research(Collins, Gluck, Walsh, Krusmark & Gunzelmann, 2016; Collins, Gluck, & Walsh, 2017), has shown that the generaliza-tion of best fitting parameters from prior data can improve initial performance predictions.Here we build on that research,using Bayesian hierarchical modeling to estimate free parameters from various sources of prior data. Bayesian hierarchalmodeling allows an opportunity to improve and add structure to the parameters used by PPE, improving its application tocognitive technology in education and training.