%0 Journal Article
%T A New Approach to Predicting Bankruptcy: Combining DEA and Multi-Layer Perceptron
%A Ayan Mukhopadhyay
%A Suman Tiwari
%A Ankit Narsaria
%A Bhaskar Roy Karmaker
%J International Journal of Computer Science Issues
%D 2012
%I IJCSI Press
%X The question of financial health and sustenance of a firm is so intriguing that it has spanned numerous studies. For investors,stakeholders and lenders, assessing the risk associated with an enterprise is vital. Several tools have been formulated to deal with predicting the solvency of a firm. This paper attempts to combine Data Envelopment Analysis and Multi-Layer Perceptron (MLP) to suggest a new method for prediction of bankruptcy that not only focusses on historical financial data of firms that filed for bankruptcy like other past studies but also takes into account the data of those firms that were likely to do so. This method thus identifies firms that have a high chance of facing bankruptcy along with those that have filed for bankruptcy. The performance of this procedure is compared with MLP. The suggested method outperforms MLP in prediction of bankruptcy.
%K Operation Research
%K Data Envelopment Analysis
%K Super Efficiency DEA
%K Bankruptcy
%K Artificial Neural Networks
%K Multi-Layer Perceptron
%K Finance.
%K IJCSI
%U http://www.ijcsi.org/papers/IJCSI-9-4-2-71-78.pdf