Personalized interpretable classification

Zengyou He, Pengju Li, Yifan Tang, Lianyu Hu, Mudi Jiang, Yan Liu

Abstract: How to interpret a data mining model has received much attention recently, because people may distrust a black-box predictive model if they do not understand how the model works. Hence, it will be trustworthy if a model can provide transparent illustrations on how to make the decision. Although many rule-based interpretable classification algorithms have been proposed, these existing solutions cannot directly construct an interpretable model to provide personalized prediction for each individual test sample. In this paper, we attempt to formally formulate and introduce personalized interpretable classification problem to the data mining society. In addition to the problem formulation on this new issue, we present a greedy algorithm called personalized interpretable classifier (PIC) to identify a personalized rule for each individual test sample. To improve the running efficiency, a fast approximate algorithm called fPIC is presented as well. To demonstrate the necessity, feasibility and advantages of such a personalized interpretable classification method, we conduct a series of empirical studies on real data sets. The experimental results show that: (1) the new problem formulation enables us to find interesting rules for test samples that may be missed by existing non-personalized classifiers. (2) Our algorithms can achieve comparable predictive accuracy to those state-of-the-art (SOTA) interpretable classifiers. (3) On a real data set for predicting breast cancer metastasis, such personalized interpretable classifiers achieve accuracy comparable to SOTA methods while providing enhanced interpretability.

External IDs:dblp:journals/kais/HeLTHJL26