Causal rule mining for knowledge discovery from databases

Data is given high importance in the real world. It is growing exponentially and potential relationships which are latent in the data can add value to enterprises. Causal relationship mining is one of the data mining approaches to discover hidden relationships that exhibit cause and effect. Identifying causal relationships and presenting in the form of rules has its high utility in decision making processes. A simple data mining approach to generate rules is Association Rule Mining (ARM) which producing frequent item sets and then rules containing association among attributes of given dataset. This is one of the suitable techniques that can be reused to discover causal relationships. The rationale behind this is that causal relationships imply associations that are mined with ARM. However, the reverse may not be true. Moreover ARM can deal with high-dimensionality issue of datasets. For this reason, in this paper, we proposed an algorithm that is based on ARM for discovering causal rules. We built a prototype application to demonstrate proof of the concept.