期刊名称：International Journal of Academic Research in Business and Social Sciences
电子版ISSN：2222-6990
出版年度：2020
卷号：10
期号：7
页码：280-295
DOI：10.6007/IJARBSS/v10-i7/7415
语种：English
出版社：Human Resource Management Academic Research Society
摘要：In recent years, data mining methods have been frequently used in financial investment decisions and the most common one is clustering. The aim of this study is to demonstrate the feasibility and availability of clustering method to propose for the most suitable investment alternative according to the socio-demographic characteristics of individual investors. In order to achieve this goal, the questionnaire method was conducted with 332 individual investors regarding their socio-demographic characteristics with investment preferences which were specified as gold, interest and stock options. Since all variables are categorical, the k-mode cluster algorithm, which is the extension of the k-mean algorithm, was implemented. The results of the analysis indicated that, apart from the risky stock alternative, only two investment options are suitable for these investors and they are risk-avoiders. Another result revealed that only gender and marital status are factors affecting investment preferences. This result will be beneficial for investment advisors to make investment suggestions to individual investors by focusing on these factors. These findings prove that clustering method can be applied effectively in determining suitable investments for individuals, since similar results have been obtained with previous studies.
