Factor Analysis of Investment Trust Products by Using Monthly Reports and News Articles

摘要

In this paper, we propose a method of factor analysis with the state space model to help people understand trust products. First, we extract the macro- and micro-factors that affect the net assets value (NAV) of investment trust products from monthly reports and news articles. The extracted factors are then classified by associating them with the categories defined in the Nikkei Thesaurus (Nihon Keizai Shimbun). After that, we select appropriate factors and then construct the state space model to analyze the degree of impact on the NAV of macro-and micro-factors based on the detection of trends in NAV and the correlation analysis of factors. We validated the proposed method based on experimental results.