Home sales index prediction model based on cluster and principal component statistical approaches in a big data analytic concept

详细信息    查看全文

• 作者：Seungwoo Han ; Yongho Ko ; Seongdo Kim ; Do Hyoung Shin
• 关键词：big data ; home sales index ; cluster analysis ; principal component analysis ; search queries
• 刊名：KSCE Journal of Civil Engineering
• 出版年：2017
• 出版时间：January 2017
• 年：2017
• 卷：21
• 期：1
• 页码：67-75
• 全文大小：
• 刊物类别：Engineering
• 刊物主题：Civil Engineering; Industrial Pollution Prevention; Geotechnical Engineering & Applied Earth Sciences;
• 出版者：Korean Society of Civil Engineers
• ISSN：1976-3808
• 卷排序：21

文摘

Data analysis has become one of the most important tools in various fields of engineering. HSI (Home Sales Index) has been considered one of the most crucial factors for predicting the economic trends in the construction industry. While a precise prediction of a HSI is very significant, it is limited due to the difficulty in collecting valuable information and analyzing that information properly. The several conducted studies related to a similar subject have mostly approached to the time series analysis with assumption that the HSI has been influenced with the past patterns such as seasons and historic issues. This paper mainly focused on the objective of presenting the performance of a new HSI prediction model using a big data analysis method focusing on social factors in high correlations in HSI without any those assumptions. In accordance with this research objective, this paper suggests a definite methodology for analyzing data and developing a related prediction model using cluster and principal component statistical approached focusing on comprehensive search queries on the Web. The significant results derived from the model applied to HSI prediction can be used as the initial phase of a big data analysis in the construction field in both academia and industry.