Parallel Decision Tree Algorithm Based on Granular Computing

Large data processing has become a hot topic of current research. How to efficiently dig out useful information from large amounts of data becomes an important research direction in the field of data mining. Firstly, some granular concept about the decision tree was introduced in this article. Secondly, referring to granular computing, the improvement and parallelization ID3 algorithms were presented. Finally, the proposed algorithms were tested on two data sets. It can be concluded that the algorithm's classification accuracy improved. From the test on Hadoop platform, the results demonstrate that the parallel algorithms can efficiently process massive datasets.