A multi-industry bankruptcy prediction model using back-propagation neural network and multivariate discriminant analysis

Lee, Sangjae; Choi, Wu Sung

doi:10.1016/j.eswa.2012.12.009

Cited by 139 publications

(84 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Among the first studies using neural networks in detecting financial distress were Odom and Sharda (1990), Wilson and Sharda (1994) and Tam and Kiang (1992). The most recently studies includes, for example Kim and Kang (2010), du Jardin (2010) or Lee and Choi (2013).…”

Section: Prior Research and Literature Reviewmentioning

confidence: 99%

Performance Comparison of Multiple Discriminant Analysis and Logit Models in Bankruptcy Prediction

Mihalovič

2016

Economics &Amp; Sociology

View full text Add to dashboard Cite

ABSTRACT. In this study, the attention is dedicated to the development of bankruptcy prediction model in Slovak Republic. The presented paper focuses on the comparison of overall prediction performance of the two developed models. The first one is estimated via discriminant analysis, while the another is based on a logistic regression. The sample is made up of 236 firms operating in Slovakia, divided into two groups -failed and non-failed firms. The results of the study suggest that the model based on a logit function outperforms the classification accuracy of the discriminant model. The most significant predictors of impeding firms´ failure appear to be Net Income to Total Assets, Current Ratio and Current liabilities to Total Assets.

show abstract

Section: Prior Research and Literature Reviewmentioning

confidence: 99%

Performance Comparison of Multiple Discriminant Analysis and Logit Models in Bankruptcy Prediction

Mihalovič

2016

Economics &Amp; Sociology

View full text Add to dashboard Cite

show abstract

“…Artificial Neural Networks (ANNs) [10][11][12][13] and Support Vector Machine (SVM) [14][15][16][17][18][19] are two commonly soft computing methods used in credit scoring modelling. Recently, other methods like evolutionary algorithms [20], stochastic optimization technique and support vector machine [21] have shown promising results in terms of prediction accuracy.…”

Section: Introductionmentioning

confidence: 99%

Credit scoring with a feature selection approach based deep learning

Nguyen

2016

MATEC Web of Conferences

View full text Add to dashboard Cite

Abstract. In financial risk, credit risk management is one of the most important issues in financial decision-making. Reliable credit scoring models are crucial for financial agencies to evaluate credit applications and have been widely studied in the field of machine learning and statistics. Deep learning is a powerful classification tool which is currently an active research area and successfully solves classification problems in many domains. Deep Learning provides training stability, generalization, and scalability with big data. Deep Learning is quickly becoming the algorithm of choice for the highest predictive accuracy. Feature selection is a process of selecting a subset of relevant features, which can decrease the dimensionality, reduce the running time, and improve the accuracy of classifiers. In this study, we constructed a credit scoring model based on deep learning and feature selection to evaluate the applicant's credit score from the applicant's input features. Two public datasets, Australia and German credit ones, have been used to test our method. The experimental results of the real world data showed that the proposed method results in a higher prediction rate than a baseline method for some certain datasets and also shows comparable and sometimes better performance than the feature selection methods widely used in credit scoring.

show abstract

“…Modelos internos más recientes pueden encontrarse en (Lee & Choi, 2013) quienes usan redes neurales y discriminantes sobre variables financieras para tratar de predecir la banca rota, (Delen, Kuzey, & Uyar, 2013) usanárboles de decisión sobre variables financieras para medir el desempeño de las empresas o (Zhou, 2013) quien muestra los efectos de distintas formas de muestreo sobre variables financieras en la capacidad de los modelos para predecir las quiebras. Es importante destacar que en todos los casos se busca distinguir entre los estados de quiebra y supervivencia de la empresa, aunque en ocasiones se busca evaluar la posibilidad de un cambio en la nota crediticia.…”

Section: Scorings De Créditounclassified

Eficiencia de los modelos Poisson y Logístico en la asignación de probabilidades de incumplimiento a empresas mineras mexicanas

Aké

Durón

Ruiz

2017

REMEF

View full text Add to dashboard Cite

A multi-industry bankruptcy prediction model using back-propagation neural network and multivariate discriminant analysis

Cited by 139 publications

References 27 publications

Performance Comparison of Multiple Discriminant Analysis and Logit Models in Bankruptcy Prediction

Performance Comparison of Multiple Discriminant Analysis and Logit Models in Bankruptcy Prediction

Credit scoring with a feature selection approach based deep learning

Eficiencia de los modelos Poisson y Logístico en la asignación de probabilidades de incumplimiento a empresas mineras mexicanas

Contact Info

Product

Resources

About