다변량 분석을 통한 분석 도구 소프트웨어 성능 비교 연구

Abstract

With the development of the Internet environment, SNS, search portal sites and various internet media have started to produce unstructured data. In addition, as the information technology developed, the storage disk can be easily obtained by the sudden price drop of the storage medium. This has led to the era of big data that can collect, analyze, utilize and predict existing structured data and unstructured data on a large storage disk. The various collected data are used in various fields. Distribution, and marketing to medical services. As the accumulated data is diversified, the reliability of the predictable probability increases and the value of the data increases. Recently, it is important to understand how fast and accurate the same data can be analyzed due to the distribution of enough storage disks. For this purpose, each company and organization develops various analysis tools, but the performance of analytical tools that handle them when analyzing large amounts of data is not considered important. As a representative analysis tool software, there are SPSS for commercial software and R for open source software. However, research on the performance of both analysis tools is lacking. In this paper, we aim to compare data analysis performance through multivariate analysis of mass data for commercial software and open source analysis tool, and to help selection of more useful analysis tools.