Using Bayesian Networks for Bankruptcy Prediction: Empirical Evidence from Iranian Companies

Aghaie, Arezoo; Saeedi, Ali

doi:10.1109/icime.2009.91

Cited by 12 publications

(6 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Research done by [1] did model development for companies getting bankrupt for the given firms using ML algorithms. They have used 21 variables which are used to select the variables for model.…”

Section: Literature Surveymentioning

confidence: 99%

Performance Evaluation of Different Machine Learning Models for Bankruptcy Prediction

Sindhu

2023

Recent Trends in Data Science and Its Applications

View full text Add to dashboard Cite

Bankruptcy of a company usually is a huge issue for companies. The bad influence of bankruptcy could lead to loss for components of the business such as the owners, the investors, the employees, and the consumers. Bankruptcy prediction is the practice of forecasting the financial distress and potential bankruptcy of a public firm. This area of research involves analyzing various financial ratios and other data to identify indicators of financial risk. We can prevent bankruptcy by predicting the likelihood of acompany getting bankrupt based on a company's financial ratios and data. With the advent of new data-intensive techniques, suchas machine learning, researchers have developed increasinglysophisticated methods for predicting bankruptcy. However, it is important to exercise caution when interpreting the results of such models, as they can suffer from biases and other limitations.Despite these challenges, bankruptcy prediction remains a critical area of study for investors and creditors seeking to assess the financial health of a company The issue of this whole processis managing the imbalance in class caused by the rare event of bankruptcy in the real economy. Advancements in Artificial Intelligence (AI) have helped these companies by applying those models to predict bankruptcy. This bankruptcy problem wassolved in this work by comparing various Machine Learning methods such as SVM, KNN, Ensemble Learning, Decision Tree classification was applied which achieved 60%, 84%, 93%, 94% accuracy.

show abstract

Section: Literature Surveymentioning

confidence: 99%

Performance Evaluation of Different Machine Learning Models for Bankruptcy Prediction

Sindhu

2023

Recent Trends in Data Science and Its Applications

View full text Add to dashboard Cite

show abstract

“…Processing elements in neural networks are much easier than conventional processors with numerous differences. [17] Each neuron with a number of other neurons to connect directly and is independent and weight of the connections will determine their relationship, the data are placed in weights. Neural net-work has the following features:…”

Section: Neural Networkmentioning

confidence: 99%

“…Units in multi-layer networks are numbered by the layers (Instead of pursuing overall numbering). [17] Both layers of a network communicate with each other by weights, In fact connections. In neural networks are some types of connection or link weight: Pioneer: More links of this type in which signals are only in one direction.…”

Section: Neural Network Structurementioning

confidence: 99%

See 1 more Smart Citation

Survey of the Euro Currency Fluctuation by Using Data Mining

Baan¹,

Saadati²,

Nasiri

2013

IJCSIT

View full text Add to dashboard Cite

Data mining or Knowledge Discovery in Databases (KDD) is a new field in information technology thatemerged because of progress in creation and maintenance of large databases by combining statisticaland artificial intelligence methods with database management. Data mining is used to recognizehiddenpatterns and provide relevant information for decision making on complex problems where conventionalmethods are inecient or too slow. Data mining can be used as a powerful tool to predict future trends andbehaviors, and this prediction allows making proactive, knowledge-driven decisions in businesses. Sincethe automated prospective analyses offered by data mining move beyond theanalyses of past eventsprovided by retrospective tools, it can answer the business questions which are traditionally timeconsuming to resolve. Based on this great advantage, it provides more interest for the government,industry andcommerce. In this paper we have used this tool to investigate the Euro currency fluctuation.For this investigation, we have three different algorithms: K*, IBK and MLP and we have extractedEuro currency volatility by using the same criteria for all used algorithms. The used dataset has21,084 records and is collected from daily price fluctuations in the Euro currency in the periodof10/2006 to 04/201

show abstract

“…Statistical Approaches in which univariate analysis (Beaver, 1966) [22], mult ivariate discriminant analysis (Altman, 1968) [21], log istic regression approach (Ohlson, 1980) [23] and factor analysis technique (West, 1985) [24] have been applied. Another approach is artificial intelligence and soft computing approaches in which artificial neural networks [25], Support vector machines [26] Bayesian network models [27] and many other AI techniques have been applied. Other then these approaches swarm intelligence approaches [28-29, 35, 37] and hybrid methods and ensemble methods [8], [25] [43] have been applied to predict bankruptcy.…”

Section: Introductionmentioning

confidence: 99%

An Analysis on Qualitative Bankruptcy Prediction Rules using Ant-Miner

Atkinson¹,

Lakshmi²,

Venkatesan³

2013

IJISA

View full text Add to dashboard Cite

Qualitative bankruptcy prediction rules represent experts' problem-solving knowledge to predict qualitative bankruptcy. The objective of this research is predicting qualitative bankruptcy using ant-miner algorithm. Qualitative data are subjective and more difficult to measure. This approach uses qualitative risk factors which include fourteen internal risk factors and sixty eight external risk factors associated with it. By using these factors qualitative prediction rules are generated using ant-miner algorithm and the influence of these factors in bankruptcy is also analyzed. Ant-Miner algorithm is a application of ant colony optimization and data mining concepts. Qualitative rules generated by ant miner algorithm are validated using measure of agreement. These prediction rules yields better accuracy with lesser number of terms than previously applied qualitative bankruptcy prediction methodologies

show abstract

Using Bayesian Networks for Bankruptcy Prediction: Empirical Evidence from Iranian Companies

Cited by 12 publications

References 9 publications

Performance Evaluation of Different Machine Learning Models for Bankruptcy Prediction

Performance Evaluation of Different Machine Learning Models for Bankruptcy Prediction

Survey of the Euro Currency Fluctuation by Using Data Mining

An Analysis on Qualitative Bankruptcy Prediction Rules using Ant-Miner

Contact Info

Product

Resources

About