Supervised Item Response Models for Informative Prediction

Abstract Supporting human decision making is a major goal of data mining. The more decision making is critical, the more interpretability is required in the predictive model. This paper proposes a new framework to build a fully interpretable predictive model for questionnaire data, while maintaining high prediction accuracy with regards to the nal outcome. Such a model has applications in project risk assessment, in health care, in social studies and presumably in any real world application that relies on questionnaire data for informative and accurate prediction.

Our framework is inspired by models in Item Response Theory (IRT), which were originally developed in psychometrics with applications to standardized tests such as SAT. We extend these models, which are essentially unsupervised, to the supervised setting. For model estimation, we introduce a new iterative algorithm by combining Gauss-Hermite quadrature with an expectation-maximization algorithm. The learned probabilistic model is linked to the metric learning framework for informative and accurate prediction. The model is validated by three real-world data sets: Two are from information technology project failure prediction and the other is an international social study about people's happiness.

To the best of our knowledge, this is the rst work that leverages the IRT framework to provide informative and accurate prediction on ordinal questionnaire
data.