Data Mining for Actionable Knowledge: A Survey

TL;DR

This survey reviews methods and frameworks for extracting actionable knowledge from data mining processes, emphasizing how to generate patterns that lead to profitable and efficient decision-making.

Contribution

It provides the first comprehensive survey on actionable knowledge in data mining, presenting two frameworks and analyzing research from different viewpoints.

Findings

Two frameworks for mining actionable knowledge are identified.

Research is categorized by data mining tasks and frameworks.

Several issues remain underexplored in actionable knowledge mining.

Abstract

The data mining process consists of a series of steps ranging from data cleaning, data selection and transformation, to pattern evaluation and visualization. One of the central problems in data mining is to make the mined patterns or knowledge actionable. Here, the term actionable refers to the mined patterns suggest concrete and profitable actions to the decision-maker. That is, the user can do something to bring direct benefits (increase in profits, reduction in cost, improvement in efficiency, etc.) to the organization's advantage. However, there has been written no comprehensive survey available on this topic. The goal of this paper is to fill the void. In this paper, we first present two frameworks for mining actionable knowledge that are inexplicitly adopted by existing research methods. Then we try to situate some of the research on this topic from two different viewpoints: 1) data mining tasks and 2) adopted framework. Finally, we specify issues that are either not addressed or insufficiently studied yet and conclude the paper.