Efficient Implementation of Hadoop MapReduce-Based Dataflow

Abstract

MapReduce is a solution for the treatment of large data. With it we can analyze and process data. It does this by distributing the computation in a large set of machines. Process mining provides an important bridge between data mining and business process analysis. This technique allows for the extraction of information from event logs. Firstly, the chapter mines small patterns from log traces. Those patterns are the representation of the traces execution from a business process. The authors use existing techniques; the patterns are represented by finite state automaton; the final model is the combination of only two types of patterns that are represented by the regular expressions. Secondly, the authors compute these patterns in parallel, and then combine those patterns using MapReduce. They have two parties. The first is the Map Step. The authors mine patterns from execution traces. The second is the combination of these small patterns as reduce step. The results are promising; they show that the approach is scalable, general, and precise. It minimizes the execution time by the use of MapReduce.