A GA-Based Support Vector Machine Diagnosis Model for Business Crisis

This research proposes a diagnosis model for business crisis integrated a real-valued genetic algorithm and support vector machine. A series of learning and testing processes with real business data show that the diagnosis model has a crisis prediction accuracy of up to 95.56%, demonstrating the applicability of the proposed method. Six features, including five financial and one intellectual capital indices, are used for the diagnosis. These features are common and easily accessible from publicly available information. The proposed GA-SVM diagnosis model can be used by firms for self-diagnosis and evaluation.