Discussion: Effective and Interpretable Outcome Prediction by Training Sparse Mixtures of Linear Experts

Abstract

Process Outcome Prediction entails predicting a discrete property of an unfinished process instance from its partial trace. High-capacity outcome predictors discovered with ensemble and deep learning methods have been shown to achieve top accuracy performances, but they suffer from a lack of transparency. Aligning with recent efforts to learn inherently interpretable outcome predictors, we propose to train a sparse Mixture-of-Experts where both the ``gate'' and ``expert'' sub-nets are Logistic Regressors. This ensemble-like model is trained end-to-end while automatically selecting a subset of input features in each sub-net, as an alternative to the common approach of performing a global feature selection step prior to model training. Test results on benchmark logs confirmed the validity and efficacy of this approach.