Effect of feature discretization on classification performance of explainable scoring-based machine learning model 

Pajor A, Sniezynski B, Zolnierek J, Sitek A

We improve the utility of the Risk-calibrated Supersparse Linear Integer Model (RiskSLIM). It is a scoring system that is an interpretable machine learning classification model optimized for performance. Scoring systems are commonly used in healthcare and justice. We implement feature discretization (FD) in the hyperparameter optimization process to improve classification performance and refer to the new approach as FD-RiskSLIM. We test the approach using two medical applications. We compare the results of FD-RiskSLIM, RiskSLIM, and other machine learning (ML) models. We demonstrate that scoring models based on RiskSLIM, in addition to being interpretable, perform at least on par with the state-of-the-art ML models such as Gradient Boosting in terms of classification metrics. We show the superiority of FD-RiskSLIM over RiskSLIM.