A Hybrid Business Failure Prediction Model Using Locally Linear Embedding and Support Vector Machines

The purpose of this paper is to propose a hybrid model which combines locally linear embedding (LLE) algorithm and support vector machines (SVM) to predict the failure of firms based on past financial performance data. By making use of the LLE algorithm to perform dimension reduction for feature extraction, is then utilized as a preprocessor to improve business failure prediction capability by SVM. The effectiveness of the methodology was verified by comparing principal component analysis (PCA) and SVM with our proposed hybrid approach. The results show that our hybrid approach not only has the best classification rate, but also produces the lowest incidence of Type I and Type II errors, and is capable to provide on time signals for better investment and government decisions with timely warnings. Keyword: business failure, manifold learning, locally linear embedding, support vector machines JEL Classification: G33,C45