Hybrid Scalable Action Rule

Action Rule mining is a method to extract actionable pattern from datasets. Classification rules are those which helps predict the object's class, whereas Action Rules are actionable knowledge that provide suggestions on how an objects state or class can be changed to a more desirable state to benefit the user. In the internet era, digital data is wide spread and growing tremendously is such way that it is neccessary to develop systems that process the data in a much faster way. The literature of Action Rule mining involves two major frameworks; Rule-Based method: where extraction of Action Rules is dependent on the pre-processing step of classification rule discovery, and Object Based Method: extracts Action Rule directly from the database without the use of classification rules. Object based method extracts Action Rule in a apriori like method using frequent action sets. Since this method is iterative it takes longer time to process huge datasets. In this work we propose a novel hybrid approach to generate complete set of Action Rules by combining the Rule-Based and Object-Based methods. Our results show a significant improvement, where the existing algorithm does not span for the Twitter dataset. On the other hand the proposed hybrid approach completed execution and produces Action Rules in less than 500 seconds on a Cluster.