Evaluation of Expert-Based Q-Matrices Predictive Quality in Matrix Factorization Models

Matrix factorization techniques are widely used to build collaborative filtering recommender systems. These recommenders aim at discovering latent variables or attributes that are supposed to explain and ultimately predict the interest of users. In cognitive modeling, skills and competencies are considered as key latent attributes to understand and assess student learning. For this purpose, Tatsuoka introduced the concept of Q-matrix to represent the mapping between skills and test items. In this paper we evaluate how predictive expert-created Q-matrices can be when used as a decomposition factor in a matrix factorization recommender. To this end, we developed an evaluation method using cross validation and the weighted least squares algorithm that measures the predictive accuracy of Q-matrices. Results show that expert-made Qmatrices can be reasonably accurate at predicting users success in specific circumstances that are discussed at the end of this paper.