Business failure, is a general term and, according to a widespread definition, is the situation that a firm can not pay lenders, preferred stock shareholders, suppliers, etc., or a bill is overdrawn, or the firm is bankrupt according to the law. All these situations result in a discontinuity of the firm's operations.
Business failure is a worldwide problem. The number of failing firms is important for the economy of a country and it can be considered as an index of the development and robustness of the economy.
The development and use of models, able to predict failure, can be very important for firms in two different ways. First, as "early warning system", such models are very useful to those (managers, authorities, etc.) that can act to prevent failure. Second, such models can be useful in aiding DMs of financial institutions in the firms' evaluation and selection.
This paper proposes the hybrid intelligent system combining neural network and rough set approach. Neural network and rough set are complements each of the other. The neural network used in hybrid model is trained with rough set preprocessed data. The effectiveness of suggested methodology is supported by experiments comparing traditional discriminant analysis and neural network approach with proposed hybrid approach.
