Interpretable Summaries of Black Box Incident Triaging with Subgroup Discovery

TL;DR

This paper introduces a subgroup discovery-based method to generate interpretable summaries of black box incident triaging models, aiding on-call engineers in understanding and automating incident severity assessments.

Contribution

The paper presents a novel data-mining approach using subgroup discovery to provide global explanations for black box models in incident triaging, addressing scalability and interpretability challenges.

Findings

Effective grouping of incidents with similar explanations

Preliminary results show promising interpretability benefits

Potential to improve automation and decision-making for engineers

Abstract

The need of predictive maintenance comes with an increasing number of incidents reported by monitoring systems and equipment/software users. In the front line, on-call engineers (OCEs) have to quickly assess the degree of severity of an incident and decide which service to contact for corrective actions. To automate these decisions, several predictive models have been proposed, but the most efficient models are opaque (say, black box), strongly limiting their adoption. In this paper, we propose an efficient black box model based on 170K incidents reported to our company over the last 7 years and emphasize on the need of automating triage when incidents are massively reported on thousands of servers running our product, an ERP. Recent developments in eXplainable Artificial Intelligence (XAI) help in providing global explanations to the model, but also, and most importantly, with local explanations for each model prediction/outcome. Sadly, providing a human with an explanation for each outcome is not conceivable when dealing with an important number of daily predictions. To address this problem, we propose an original data-mining method rooted in Subgroup Discovery, a pattern mining technique with the natural ability to group objects that share similar explanations of their black box predictions and provide a description for each group. We evaluate this approach and present our preliminary results which give us good hope towards an effective OCE's adoption. We believe that this approach provides a new way to address the problem of model agnostic outcome explanation.