Actionable Analytics: Stop Telling Me What It Is; Please Tell Me What To Do
Chakkrit Tantithamthavorn, Jirayus Jiarpakdee, John Grundy
Abstract
The success of software projects depends on complex decision making (e.g., which tasks should a developer do first, who should perform this task, is the software of high quality, is a software system reliable and resilient enough to deploy, etc.). Bad decisions cost money (and reputation) so we need better tools for making better decisions. This article discusses the "why" and "how" of explainable and actionable software analytics. For the task of reducing the risk of software defects, we show initial results from a successful case study that offers more actionable software analytics. Also, we present an interactive tutorial on the subject of Explainable AI tools for SE in our Software Analytics Cookbook (https://xai4se.github.io/book/), and we discuss some open questions that need to be addressed.