Financial Instruments Recommendation based on Classification Financial Consumer by Text Mining Techniques

Submitted:December 6, 2016 1 st Revision:December 19, 2016 Accepted:December 23, 2016 * 본 연구는 정부(미래창조과학부)의 재원으로 정보통신기술진흥센터의 지원을 받아 수행된 연구임(No. R0126-15-1007). ** 경희대학교 일반대학원 경영학과 *** 경희대학교 경영대학 경영연구원 연구원 **** 경희대학교 경영대학, 교신저자 With the innovation of information technology, non-face-to-face robo advisor with high accessibility and convenience is spreading. The current robot advisor recommends appropriate investment products after understanding the investment propensity based on the structured data entered directly or indirectly by individuals. However, it is an inconvenient and obtrusive way for financial consumers to inquire or input their own subjective propensity to invest. Hence, this study proposes a way to deduce the propensity to invest in unstructured data that customers voluntarily exposed during consultation or online. Since prediction performance based on unstructured document differs according to the characteristics of text, in this study, classification algorithm optimized for the characteristic of text left by financial consumers is selected by performing prediction performance evaluation of various learning discrimination algorithms and proposed an intelligent method that automatically recommends investment products. User tests were given to MBA students. After showing the recommended investment and list of investment products, satisfaction was asked. Financial consumers' satisfaction was measured by dividing them into investment propensity and recommendation goods. The results suggest that the users high satisfaction with investment products recommended by the method proposed in this paper. The results showed that it can be applies to non-face-to-face robo advisor. Keyword:Fintech, Robo-Advisor, Text Mining, Decision Tree, Random Forest, Machine learning 韓國IT서비스學會誌 第15卷 第4號 2016年 12月, pp.1-24 2 Jaewoong Lee.Young-Sik Kim.Ohbyung Kwon