RuDi: Explaining Behavior Sequence Models by Automatic Statistics Generation and Rule Distillation

TL;DR

RuDi is a two-stage method that automatically generates informative statistics and distills black-box behavior sequence models into transparent rule-based models, enhancing explainability in risk scoring.

Contribution

It introduces a novel Monte Carlo tree search-based statistics generation and neural logical networks for rule distillation from black-box models.

Findings

Effective on multiple real-world datasets

Produces interpretable rule-based models

Maintains high predictive performance

Abstract

Risk scoring systems have been widely deployed in many applications, which assign risk scores to users according to their behavior sequences. Though many deep learning methods with sophisticated designs have achieved promising results, the black-box nature hinders their applications due to fairness, explainability, and compliance consideration. Rule-based systems are considered reliable in these sensitive scenarios. However, building a rule system is labor-intensive. Experts need to find informative statistics from user behavior sequences, design rules based on statistics and assign weights to each rule. In this paper, we bridge the gap between effective but black-box models and transparent rule models. We propose a two-stage method, RuDi, that distills the knowledge of black-box teacher models into rule-based student models. We design a Monte Carlo tree search-based statistics generation method that can provide a set of informative statistics in the first stage. Then statistics are composed into logical rules with our proposed neural logical networks by mimicking the outputs of teacher models. We evaluate RuDi on three real-world public datasets and an industrial dataset to demonstrate its effectiveness.