• Selected
• Entire List

Abstract:
This exploratory research examines and models the financial distress prediction using neural network approach. The study is based on financial ratios. Nine different neural network models are constructed to test the predictive capability of the models by considering: (1) the impact of time varying information structure prior the distressed situation using first, independent annual financial ratios (four models)and second, different panel data sets (three models) and, (2) the influence of time varying probability estimates of financial distress in panel data sets (two models). Results support that it is not necessary to have complex architecture in neural models to predict firm's financial distress. Besides more the predictability horizon is shorter and the input information structure is most recent, more the predictive capability of the neural model is better.

financial distress, neural network, risk management

Abstract:
This study examines the association between different institutional investors’ ownership and earnings management practice using a neural networks approach. It investigates this relationship for a sample of 121 US firms. We examine also the effect of institutional ownership on the level of accruals management of firms having different information environment (S&P 500 versus non S&P 500). Results show that the involvement of pension funds and banks in the firms’ capitals limit earnings management behaviors. However, investment funds ownership incites to increase earnings. The hypothesis of the relevance of the environment information in the explanation of the institutional investors’ behavior doesn’t seem to be important in our case.

institutional ownership, earnings management, discretionary accruals, neural networks

Abstract:
This paper examines the relation between the external financing cost and the choice of the investment timing. Contrary to Lyandres (2007), this paper not only takes in consideration the variation of the investment but also the variation of its payoff. Results show that firms don't present the same degree of the investment-cash-flow sensitivity since this relation, which seems to be non-monotonic, is influenced by the evolutions of the financial cost and the investment amount.

External financing, Investment, Cash flow

Abstract:
This paper examines and models the financial distress prediction using neural network approach. Nine different neural network models, considering various predicting time horizons and information structures, are considered. in order to test models' predictive capability we used a set of 15 financial ratios. Based on financial statements (balance-sheets, result accounts and cash flow statements) for 87 Tunisian firms from 1993 to 1996, results prove that more the predictability horizon is short and the input information structure recent, more and better is the predictive capability of the neural model. Short debt, capital structure and sales growth and liability ratios contribute meaningfully in discriminating and predicting the firm financial distress. the best model is based on the information structure giving the best predictive capability.

financial distress, neural networks, financial ratios