Predicting a corporate financial crisis using letters to shareholders
- PDF / 1,436,504 Bytes
- 14 Pages / 595.276 x 790.866 pts Page_size
- 120 Downloads / 252 Views
(0123456789().,-volV)(0123456789(). ,- volV)
METHODOLOGIES AND APPLICATION
Predicting a corporate financial crisis using letters to shareholders Yuh-Jen Chen1
· Chia-Yen Wu1
© Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract This study utilizes the textual financial information—letters to shareholders to propose a scheme for corporate financial crisis prediction instead of traditional numerical financial ratios. In the scheme, the letters to shareholders were first parsed and analyzed to establish a library of financial crisis feature terms. Based on the financial crisis feature term library, queen genetic algorithm and support vector machine were then used to classify letters to shareholders (i.e., financial crisis and non-financial crises). This scheme can effectively enhance the accuracy of corporate financial crisis detection and reduce the resulting capital damage to enterprises and investors. To achieve the above objective, the following tasks were performed: (1) a process for predicting corporate financial crises by using letters to shareholders was designed, (2) techniques involved in the process of financial crisis prediction were developed, and (3) the use of the proposed approach was demonstrated and evaluated. Keywords Financial crisis prediction · Letter to shareholders · Support vector machine (SVM) · Queen genetic algorithm (QGA)
1 Introduction Recent subprime mortgage and financial crises have influenced enterprises globally and have resulted in numerous bankruptcies. Moreover, in recent years, the openness and liberalization of the financial market have caused the rapid development of the domestic capital market. Large-scale enterprises raise funds from the public and from financial institutions; thus, the operation and management of businesses are tightly connected to social trends. If such an enterprise experiences a financial crisis, not only the enterprise, its internal management, and its staff but also its investors, creditors, financial institutions, upstream and downstream vendors, and consumers are affected by social instability. Various approaches have been proposed related to the study of corporate financial crisis prediction. For example, Chen and Hsiao (2008) established a diagnosis model for Communicated by V. Loia. & Yuh-Jen Chen [email protected] 1
Department of Accounting and Information Systems, College of Business Intelligence, National Kaohsiung University of Science and Technology, Kaohsiung, Taiwan, ROC
business crises by integrating a real-valued genetic algorithm to determine the optimum parameters and a support vector machine (SVM) to conduct learning using data and data classification. Only six influential features pertaining to intellectual capital and financial features were included in the proposed model after a two-phase selection process; the six features are ordinary and widely available in public business reports. Sun and Li (2008) suggested a financial distress prediction method based on a weighted majority voting combination of multipl
Data Loading...
