Developing an Risk Signal Detection System Based on Opinion Mining for Financial Decision Support

Abstract

Companies have long sought to detect financial risks and prevent crises in their business activities. Investors also have a great need to identify risks and utilize them for investment. Thus, several studies have attempted to detect financial risk. However, these studies had limitations in that various data were not exploited and diverse perspectives of the firm were not reflected. This can lead to wrong choices for investment. Thus, the purpose of this study was to propose risk signal prediction models based on firm data and opinion mining, reflecting both the perspectives of firms and investors. Furthermore, we developed a process to obtain real time firm related data and convenience visualization. To develop this process, a credit event was defined as an event that led to a critical risk of the firm. In the next step, the firm risk score was calculated for a firm having a possible credit event. This score was calculated by combining the firm activity score and opinion mining score. The firm activity score was calculated based on a financial statement and disclosure data indicator, while the opinion mining score was calculated based on a sentiment analysis of news and social data. As a result, the total firm risk grade was derived, and the risk level was proposed. These processes were developed into a system and illustrated by real firm data. The results of this study demonstrate that it is possible to derive risk signals through integrated monitoring indicators and provide useful information to users. This study can help users make decisions. It also provides users an opportunity to identify new investment momentums.