ABSTRACT
A failure or distress prediction model can be used by financial institutions to assess the financial health of a company in order to calculate the likelihood of recovering a loan or an investment. Such models can also be used as a early warning system in order to initiate change or proactive turnaround. However, problems are associated to prediction models that must be made clear. For example, if a failure prediction model based on financial ratios indicates that a company is highly likely to fail, the very same model does not indicate in any way 'what' has gone wrong, because financial ratios are symptomatic rather than causal by nature. Examples are known were managers with such knowledge have tried to improve the ratios in various ways without addressing the real problems. There are also examples of the use of failure prediction models to focus managers' attention on the real problems (Altman, 1993). As a result, it is of much interest whether models can be developed that are based on variables that are more indicative as to the cause of firms' problems or well-being.
