Bankruptcy prediction for Japanese corporations using support vector machine, artiﬁcial neural network, and multivariate discriminant analysis

Matsumaru, Masanobu; Kaneko, Shoichi; Katagiri, Hideki; Kawanaka, Takaaki

doi:10.46254/j.ieom.20190106

Cited by 3 publications

(1 citation statement)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, machine learning has been widely used for different applications in the finance sector. Matsumaru et al (2019) proposed models for predicting bankruptcy risk in companies, making use of a multiple discriminant analysis, artificial neural networks and support vector machines. Data from 64,708 companies in Japan from the period between 1991 and 2015 were used to assess models for predicting bankruptcy from different types of industries.…”

Section: Literature Reviewmentioning

confidence: 99%

Machine Learning in Finance: An Application of Predictive Models to Determine the Payment Probability of a Client

Proceedings of the International Conference on Industrial Engineering and Operations Management

View full text Add to dashboard Cite

In the last decades, private debt collection has become an important industry in Ecuador. Debt collection Agencies are organizations that manage the process of collecting money from delinquent debts and their performance is often measured by the collection success rate. However, determining which clients will repay their liabilities is a complex process and many times subjectively judged. Machine learning (ML) models have been successfully implemented on the financing sector for various applications, however a limited amount of work has been published in the prediction of a client´s debt payment probability. In this study, ML models are trained to predict a client´s payment probability to an Ecuadorian Debt Collection Agency the first three months after signing a payment agreement. Specifically, a feedforward neural network, logistic regression, and gradient boosting ensemble models are implemented using the SEMMA data mining methodology, which comprises the steps of sample, explore, modify, model, and assess. Furthermore, by analyzing the results of the models, relevant features that determine whether a costumer will pay or not its debt are identified. The results show that neural networks perform better than the competing models in terms of classification accuracy.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Machine Learning in Finance: An Application of Predictive Models to Determine the Payment Probability of a Client

Proceedings of the International Conference on Industrial Engineering and Operations Management

View full text Add to dashboard Cite

show abstract

Does ESG Predict Business Failure in Brazil? An Application of Machine Learning Techniques

Kaleem,

Raza,

Ashraf

et al. 2024

Risks

View full text Add to dashboard Cite

The aim of this study is to explore the influence of environmental, social, and governance (ESG) factors on business failure in Brazil by employing advanced machine learning techniques. We collected data from 235 companies and conducted principal component analysis (PCA) on 40 variables already used in the bankruptcy failure literature, resulting in the formation of seven variables that predict business failure. The results indicate that ESG factors significantly predict business failure in Brazil. This study has implications for investors, policymakers, and business leaders, offering a more precise tool for risk assessment and strategic decision-making.

show abstract

Predicting Average Wait-Time of COVID-19 Test Results and Efficacy Using Machine Learning Algorithms

Hijry

Olawoyin

Edwards

et al. 2021

IJIEOM

View full text Add to dashboard Cite

Due to the rising number of confirmed positive tests, the global impact of COVID-19 continues to grow. This can be attributed to the long wait times patients face to receive COVID-19 test results. During these lengthy waiting periods, people become anxious, especially those who are not experiencing early COVID-19 symptoms. This study aimed to develop models that predict waiting times for COVID-19 test results based on different factors such as testing facility, result interpretation, and date of test. Several machine learning algorithms were used to predict average waiting times for COVID-19 test results and to find the most accurate model. These algorithms include neural network, support vector regression, K-nearest neighbor regression, and more. COVID-19 test result waiting times were predicted for 54,730 patients recorded during the pandemic across 171 hospitals and 14 labs. To examine and evaluate the model’s accuracy, different measurements were applied such as root mean squared and R-Squared. Among the eight proposed models, the results showed that decision tree regression performed the best for predicting COVID-19 test results waiting times. The proposed models could be used to prioritize testing for COVID-19 and provide decision makers with the proper prediction tools to prepare against possible threats and consequences of future COVID-19 waves.

show abstract

Bankruptcy prediction for Japanese corporations using support vector machine, artiﬁcial neural network, and multivariate discriminant analysis

Cited by 3 publications

References 40 publications

Machine Learning in Finance: An Application of Predictive Models to Determine the Payment Probability of a Client

Machine Learning in Finance: An Application of Predictive Models to Determine the Payment Probability of a Client

Does ESG Predict Business Failure in Brazil? An Application of Machine Learning Techniques

Predicting Average Wait-Time of COVID-19 Test Results and Efficacy Using Machine Learning Algorithms

Contact Info

Product

Resources

About