Bankruptcy risk prediction models based on artificial neural networks

Doina, Prodan-Palade

doi:10.20869/auditf/2017/147/418

Cited by 4 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is difficult to be competent. In response to the above problems, many improved fast learning algorithms have been proposed at home and abroad [26][27]. These fast learning algorithms can be divided into two main categories: one is the improved heuristic learning algorithm by analyzing the gradient of the error performance function, such as the momentum BP algorithm, the BP algorithm with variable learning rate, etc .…”

Section: Improved Bp Neural Network Algorithmmentioning

confidence: 99%

Neural Network in the Forecast of Compensation for Ecological Environment Damage Caused by Trade

2021

IJFS

View full text Add to dashboard Cite

With the rapid growth of China's trade, the aggravation of environmental damage, research on trade growth and environmental damage forecasting issues is of great significance for the formulation and coordination of trade policies, environmental policies, and industrial policies. This article mainly studies the application of neural network in the prediction of compensation for ecological environment damage caused by trade. In this paper, the neural network model is applied to time series forecasting and panel data forecasting respectively, and the MATLAB tool is used to simulate the model, and the environmental damage compensation caused by trade is predicted. After L = 7613 iteration training, the total error value gradually decreases, and the given total error accuracy is 0.001. At this point, training is complete. After training, the BP neural network has been able to correctly predict these training samples. The prediction accuracy of this study reached 98%. This shows that the BP neural network model established in this paper not only meets the overall classification accuracy, but also has high accuracy in predicting the compensation of the ecological environment damage of each sample data. The research results show that the model is applied to the prediction of compensation for eco-environmental damage caused by trade. It has the advantages of fewer samples, high prediction accuracy, and simple calculation. It provides a new way to study the prediction of environmental damage caused by trade.

show abstract

Section: Improved Bp Neural Network Algorithmmentioning

confidence: 99%

Neural Network in the Forecast of Compensation for Ecological Environment Damage Caused by Trade

2021

IJFS

View full text Add to dashboard Cite

show abstract

“…The literature [16] used the entropy value method, established a prediction and early warning model of fpga and radiation-based functional neural network, and also obtained data from the model to evaluate and analyze the financial risk for five years. The literature [17] used two artificial neural network models based on correlated financial ratios and a backpropagation algorithm to predict bankruptcy risk, and the model was implemented and tested using PyBrain. The literature [18] constructed an AHP-FUZZY model based on international standards and evaluated the seven types of risks present in Internet finance.…”

Section: Introductionmentioning

confidence: 99%

A deep learning model-based approach to financial risk assessment and prediction

Li,

2023

Applied Mathematics and Nonlinear Sciences

View full text Add to dashboard Cite

This paper proposes a split-lending network model for bank credit risk, calculates whether a bank fails by simulating the changes in bank assets and liabilities over time, and adds the default rate calculation considering the characteristics of the default rate when a bank borrows. Meanwhile, the XGBoost-based classifier is used instead of random forest to improve the accuracy of classification, and the grcForest_XGB model is established. The activation function Sigmoid, the error function mean square error function, and the adam optimization function with the best effect at present are used to predict the accuracy of the grcForest_XGB model, and the different models are compared with the grcForest model for comparison experiments. The experiments show that the grcForest model has higher AUC and KS metrics of 0.8224 and 0.6368, respectively. The recall value is 0.8319, which ranks first among the six models. The Acc value is 0.9732, which is only 0.05 lower than LSTM, and is at a higher level. This study shows that the model is more accurate for risk assessment, can predict financial risks in advance, and make an effective assessment of financial risks.

show abstract

“…Today is the era of big data, with the continuous development of information technology and the strengthening of the ability of computers to process information, deep learning has become popular [4,5]. By using deep learning, more data features can be learned automatically, replacing manually designed features, and it can process tensor data, that is, multidimensional data, and learn more information contained in data [6].…”

Section: Introductionmentioning

confidence: 99%

Enterprise Financial Risk Early Warning Based on Deep Neural Network

2021

View full text Add to dashboard Cite

The occurrence of financial risk will have a great impact on the continuous operation of enterprises, which may lead to significant losses of enterprises and even cause bankruptcy of enterprises. With the increasing downward pressure on the domestic economy, economic transformation and upgrading, and the black swan event of the novel coronavirus epidemic, the operational pressure on listed companies has continued to increase, and the delisting risk of listed companies has gradually emerged. This paper mainly studies the enterprise financial risk early warning based on deep NN(NN). This paper first defines the concept of financial early warning and BP NN, and uses BP NN to construct the financial risk early warning model of listed companies. The model is trained and empirically analyzed. The results of empirical analysis show that the research of this paper is conducive to the development of indicators and methods for the prediction of financial risks of listed enterprises, which is conducive to the reference of regulators and investors.

show abstract

Bankruptcy risk prediction models based on artificial neural networks

Abstract: The purpose of this research is to study the ability of artificial neural networks to forecast the companies '

Cited by 4 publications

References 15 publications

Neural Network in the Forecast of Compensation for Ecological Environment Damage Caused by Trade

Neural Network in the Forecast of Compensation for Ecological Environment Damage Caused by Trade

A deep learning model-based approach to financial risk assessment and prediction

Enterprise Financial Risk Early Warning Based on Deep Neural Network

Contact Info

Product

Resources

About