Comparative analysis of data mining techniques for financial data using parallel processing

Abstract

The purpose of this research paper is to study the application of data mining techniques in risk analysis of financial credit related data. In the first part we will apply data mining techniques like Classification, Decision Trees, Clustering and Association Rule Mining to identify the risk associated with credit related data. The advantages, disadvantages and accuracy of each technique will be identified. In the second part we will scale and optimize the performance of these techniques using parallel computing based on multi-core CPU and GPU (GPGPU) using NVIDIA CUDA based computing framework for General-Purpose computation on GPU. The final outcome of this research is the results of the application of these algorithms and their performance statistics on CPU and GPU.