Selected Methods of Predicting Financial Health of Companies: Neural Networks Versus Discriminant Analysis (original) (raw)
Related papers
African Journal of Business Management, 2013
The objective of the paper is to assess the quality of neural networks in predicting distress as against discriminant analysis and its applications in enhancing managers' decision. Forty four firms listed on the Nigerian Stock Market between 1987 and 2006 are used for the study. The performance of neural network is then compared with the more familiar discriminant analysis statistical technique, and the performance of both is further with a performance obtainable by mere guesswork. The results show that, while both the neural network and the discriminant analysis techniques performed better than guess work, the neural network out performs the discriminant analysis technique. The outstanding performance of neural network underscores its importance as an invaluable tool in the business decision-making process. The study suggests that neural networks could aid managers in decision making to reverse the present down trend of the Nigerian Stock Market.
Qualitative company performance evaluation: Linear discriminant analysis and neural network models
European Journal of Operational Research, 1999
In this paper, we present a classification model to evaluate the performance of companies on the basis of qualitative criteria, such as organizational and managerial variables. The classification model evaluates the eligibility of the company to receive state subsidies for the development of high tech products. We furthermore created a similar model using the backpropagation learning algorithm and compare its classification performance against the linear model. We also focus on the robustness of the two approaches with respect to uncertain information. This research shows that backpropagation neural networks are not superior to LDA-models (Linear Discriminant Analysis), except when they are given highly uncertain information. 贸 1999 Elsevier Science B. V. All rights reserved.
In this paper, we present a classi®cation model to evaluate the performance of companies on the basis of qualitative criteria, such as organizational and managerial variables. The classi®cation model evaluates the eligibility of the company to receive state subsidies for the development of high tech products. We furthermore created a similar model using the backpropagation learning algorithm and compare its classi®cation performance against the linear model. We also focus on the robustness of the two approaches with respect to uncertain information. This research shows that backpropagation neural networks are not superior to LDA-models (Linear Discriminant Analysis), except when they are given highly uncertain information. Ó
Estudios Gerenciales, 2019
The aims of the present article are to identify the economic-financial indicators that best characterize Brazilian public companies through credit-granting analysis and to assess the most accurate techniques used to forecast business bankruptcy. Discriminant analysis, logistic regression and neural networks were the most used methods to predict insolvency. The sample comprised 121 companies from different sectors, 70 of them solvent and 51 insolvent. The conducted analyses were based on 35 economic-financial indicators. Need of working capital for net income, liquidity thermometer, return on equity, net margin, debt breakdown and equity on assets were the most relevant economic-financial indicators. Neural networks recorded the best accuracy and the Receiver Operating Characteristic Curves (ROC curve) corroborated this outcome.
Nova Economia, 2005
This paper looks at the ability of a relatively new technique, hybrid ANN's, to predict corporate distress in Brazil. These models are compared with traditional statistical techniques and conventional ANN models. The results suggest that hybrid neural networks outperform all other models in predicting firms in financial distress one year prior to the event. This suggests that for researchers, policymakers and others interested in early warning systems, hybrid networks may be a useful tool for predicting firm failure.
Ekonomichny visnik DVNZ UDKhTU, 2020
The article is devoted to the substantiation of the choice of financial indicators for discriminant and neural network models for diagnosing the financial condition of innovative active enterprises and determining the probability of their bankruptcy, as well as the construction of these models based on a study of the financial condition of 36 enterprises. The modern imperative of the successful development of the domestic economy is its transition to the rails of innovative development. This process is impossible without competent distribution of financial resources by business entities. In this regard, especially important is the question regarding the development of new approaches and methods for the assessment of readiness of enterprises for implementation of innovation activities due to which investors or, indeed, the state itself will be able to determine the amount of financial resources which is necessary for the development and implementation of new technologies, products or services. It is shown the importance of researching the financial condition of Ukrainian enterprises that are engaged in innovations, since their innovative activity is almost entirely financed by own means. With the aid of Deductor analytical platform, a discriminant model for assessing the financial situation and the probability of bankruptcy for innovative enterprises was built. The neural network model, which together with the analysis «if-then» gives an adequate forecast of the financial state of enterprises engaged in innovation activity, was substantiated and built. Five financial ratios (X1, X2, X3, X4 and X5) are selected and calculated for the analysis of the financial condition of 36 enterprises. For all the studied enterprises (both bankrupt and those against which bankruptcy proceedings were not initiated), the satisfactory forecast was for 30 out of 36 enterprises (83.33%), unsatisfactory for 2 enterprises (5.56%), in the gray zone there were 4 enterprises (11.11%). It is shown that the built neural network model provides forecasts of the financial condition of enterprises and the probability of their bankruptcy at a level significantly higher than discriminant models. The neural network model takes into account the specifics of domestic economic activity of enterprises, because it is built on the basis of financial data of Ukrainian enterprises.
Lecture Notes in Computer Science, 2003
This study investigated whether two artificial neural networks (ANNs), multilayer perceptron (MLP) and hybrid networks using statistical and ANN approaches, can outperform traditional statistical models for predicting corporate failures in Australia one year and two years prior to the financial distress. The results suggest that hybrid neural networks outperform all other models one and two years before failure. Therefore, hybrid neural network model is a very promising tool for failure prediction. This supports the conclusion that for shareholders, policymakers and others interested in early warning systems, hybrid networks would be useful.
Sustainability, 2020
Predicting the risk of financial distress of enterprises is an inseparable part of financial-economic analysis, helping investors and creditors reveal the performance stability of any enterprise. The acceptance of national conditions, proper use of financial predictors and statistical methods enable achieving relevant results and predicting the future development of enterprises as accurately as possible. The aim of the paper is to compare models developed by using three different methods (logistic regression, random forest and neural network models) in order to identify a model with the highest predictive accuracy of financial distress when it comes to industrial enterprises operating in the specific Slovak environment. The results indicate that all models demonstrated high discrimination accuracy and similar performance; neural network models yielded better results measured by all performance characteristics. The outputs of the comparison may contribute to the development of a repu...
Bankruptcy prediction using neural networks
Decision Support Systems, 1994
Prediction of firm bankruptcies have been extensively studied in accounting, as all stakeholders in a firm have a vested interest in monitoring its financial performance. This paper presents an exploratory study which compares the predictive capabilities for firm bankruptcy of neural networks and classical multivariate discriminant analysis. The predictive accuracy of the two techniques is presented within a comprehensive, statistically sound framework, indicating the value added to the forecasting problem by each technique. The study indicates that neural networks perform significantly better than discriminant analysis at predicting firm bankruptcies. Implications of our results for the accounting professional, neural networks researcher and decision support system builders are highlighted.
Application of Discriminant Analysis to Diagnose the Financial Distress
Theoretical Economics Letters, 2019
Prediction of bankruptcy is a critical work. This study is case based research of Ruchi Soya Ltd. to identify the financial distress with the help of last six years data and information. The bankruptcy of the organization can be predicted by using the Altman's Z score model belonging to manufacturing and non-manufacturing and private and public limited firms. This study used discriminant analysis taken the reference of altman's Z score model. Study used various ratios like working capital to total asset, retained earnings to total asset, earnings before interest and tax to total assets, market value of equity to book value of debt and sales to total assets. The analysis conducted on Ruchi Soya Ltd. to identify how and when company identifies the risk of failure. This is a case study method research which satisfies the use of Z score model to identify the bankruptcy of the company. The secondary data for the assessment were obtained from the financial statement of the company. This study would be used to discuss how to identify the bankruptcy if a firm with the help of Altman's Z score model. Research on financial health using Altman's score is very limited in Indian context. Therefore, this study focuses on applying and interpreting the financial performance of Ruchi Soya Ltd. which files bankruptcy in the year 2017.