Predicting credit risk on the basis of financial and non-financial variables and data mining

2018 ◽  
Vol 17 (3) ◽  
pp. 316-340 ◽  
Author(s):  
Sihem Khemakhem ◽  
Younes Boujelbene
Keyword(s):  
Data Mining ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Credit Risk ◽  
Decision Trees ◽  
Class Imbalance ◽  
Data Sets ◽  
Content Type ◽  
Financial Variables ◽  
Artificial Neural

PurposeData mining for predicting credit risk is a beneficial tool for financial institutions to evaluate the financial health of companies. However, the ubiquity of selecting parameters and the presence of unbalanced data sets is a very typical problem of this technique. This study aims to provide a new method for evaluating credit risk, taking into account not only financial and non-financial variables, but also the class imbalance.Design/methodology/approachThe most significant financial and non-financial variables were determined to build a credit scoring model and identify the creditworthiness of companies. Moreover, the Synthetic Minority Oversampling Technique was used to solve the problem of class imbalance and improve the performance of the classifier. The artificial neural networks and decision trees were designed to predict default risk.FindingsResults showed that profitability ratios, repayment capacity, solvency, duration of a credit report, guarantees, size of the company, loan number, ownership structure and the corporate banking relationship duration turned out to be the key factors in predicting default. Also, both algorithms were found to be highly sensitive to class imbalance. However, with balanced data, the decision trees displayed higher predictive accuracy for the assessment of credit risk than artificial neural networks.Originality/valueClassification results depend on the appropriateness of data characteristics and the appropriate analysis algorithm for data sets. The selection of financial and non-financial variables, as well as the resolution of class imbalance allows companies to assess their credit risk successfully.

Forecasting Islamic securities index using artificial neural networks: performance evaluation of technical indicators

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Faheem Aslam ◽  
Khurrum S. Mughal ◽  
Ashiq Ali ◽  
Yasir Tariq Mohmand
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Sine Wave ◽  
Machine Learning Algorithms ◽  
Data Sets ◽  
Content Type ◽  
Parameter Instability ◽  
Out Of Sample ◽  
Selection Step ◽  
Artificial Neural

PurposeThe purpose of this study is to develop a precise Islamic securities index forecasting model using artificial neural networks (ANNs).Design/methodology/approachThe data of daily closing prices of KMI-30 index span from Aug-2009 to Oct-2019. The data of 2,520 observations are divided into training and test data sets by using the 80:20 ratio, which corresponds to 2016 and 504 observations, respectively. In total, 25 features are used; however, in model selection step, based on maximum accuracy, top ten indicators are selected from several iterations of predictive models.FindingsThe results of feature selection show that top five influencing indicators on Islamic index include Bollinger Bands, Williams Accumulation Distribution, Aroon Oscillator, Directional Movement and Forecast Oscillator while Mesa Sine Wave is the least important. The findings show that the model captures much of the trend and some of the undulations of the original series.Practical implicationsThe findings of this study may have important implications for investment and risk management by using index-based products.Originality/valueNumerous studies proved that traditional econometric techniques face significant challenges in out-of-sample predictability due to model uncertainty and parameter instability. Recent studies show an upsurge of interest in machine learning algorithms to improve the prediction accuracy.

Revealing the importance of international and domestic cooperation by using artificial neural networks: case of European radical and incremental innovators

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Viktor Prokop ◽  
Jan Stejskal ◽  
Beata Mikusova Merickova ◽  
Samuel Amponsah Odei
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
International Cooperation ◽  
Incremental Innovation ◽  
Content Type ◽  
Innovation Activities ◽  
Design Activities ◽  
Artificial Neural ◽  
The One ◽  
Innovation Processes

PurposeThe purpose of this study is to introduce innovative ideas into the treatment of the radical and incremental innovations and to fill the research gap by using: (1) methods that can perform complicated tasks and solve complex problems leading in creation of radical and incremental innovation and (2) a broad sample of firms across countries. The authors’ ambition is to contribute to the scientific knowledge by producing evidence about the novel usage of artificial neural network techniques for measuring European firms' innovation activities appearing in black boxes of innovation processes.Design/methodology/approachIn this study, the authors incorporate an international context into Chesbrough's open innovation (OI) theory and, on the one hand, support the hypothesis that European radical innovators benefit more from foreign cooperation than incremental innovators. On the other hand, the results of the analyses show that European incremental innovators rely on domestic cooperation supported by cooperation with foreign public research institutes. Moreover, the use of decision trees (DT) allows the authors to reveal specific patterns of successful innovators emerging within the hidden layers of neural networks.FindingsThe authors prove that radical European innovators using either internal or external R&D strategies, while the combinations of these strategies do not bring successful innovation outputs. In contrast, European incremental innovators benefit from various internal R&D processes in which engagement in design activities plays a crucial role.Originality/valueThe authors introduce innovative ideas into the treatment of hidden innovation processes and measuring the innovation performance (affected by domestic or international cooperation) of European firms. The approach places emphasis on the novelty of innovation and the issue of international cooperation in the era of OI by designing the framework using a combination of artificial neural networks and DT.

Sign in / Sign up

Export Citation Format

Share Document