Identification of a standard AI based technique for credit risk analysis

2016 ◽  
Vol 23 (5) ◽  
pp. 1381-1390 ◽  
Author(s):  
M. Punniyamoorthy ◽  
P. Sridevi
Keyword(s):  
Neural Network ◽  
Risk Assessment ◽  
Credit Risk ◽  
Financial Institutions ◽  
Support Vector ◽  
Data Set ◽  
Content Type ◽  
Machine Learning Classification ◽  
Credit Risk Assessment ◽  
Data Points

Purpose – Credit risk assessment has gained importance in recent years due to global financial crisis and credit crunch. Financial institutions therefore seek the support of credit rating agencies to predict the ability of creditors to meet financial persuasions. The purpose of this paper is to construct neural network (NN) and fuzzy support vector machine (FSVM) classifiers to discriminate good creditors from bad ones and identify a best classifier for credit risk assessment. Design/methodology/approach – This study uses artificial neural network, the most popular AI technique used in the field of financial applications for classification and prediction and the new machine learning classification algorithm, FSVM to differentiate good creditors from bad. As membership value on data points influence the classification problem, this paper presents the new FSVM model. The instances membership is computed using fuzzy c-means by evolving a new membership. The FSVM model is also tested on different kernels and compared and the classifier with highest classification accuracy for a kernel is identified. Findings – The paper identifies a standard AI model by comparing the performances of the NN model and FSVM model for a credit risk data set. This work proves that that FSVM model performs better than back propagation-neural network. Practical implications – The proposed model can be used by financial institutions to accurately assess the credit risk pattern of customers and make better decisions. Originality/value – This paper has developed a new membership for data points and has proposed a new FCM-based FSVM model for more accurate predictions.

To Optimize a BP Network System

2011 ◽  
Vol 50-51 ◽  
pp. 919-923
Author(s):  
Wei Tong ◽  
Li Ping Qin
Keyword(s):  
Neural Network ◽  
Risk Assessment ◽  
Credit Risk ◽  
Network Model ◽  
Neural Network Model ◽  
Network System ◽  
Data Set ◽  
Bp Network ◽  
Credit Risk Assessment ◽  
The Neural Network

The neural network has been introduced into the studies of credit risk assessment. However, the ratio of the dataset for training and testing is difficult to determine, so the neural network is not robust enough to give the judgment. Therefore, using the 2000 instances of personal consumer credit data set for approval of credit applications of a provincial-level China Construction Bank, for the BP neural network model, the study focused on the ratio of the dataset for training and testing. The results show that, when the ratio of the dataset for training and testing is 800:1200, the neural network model 2 for credit risk assessment has better performance. And it can achieve the desired accuracy and computational efficiency, so the BP network system for credit risk assessment is optimized.

Credit risk assessment using purchase order information

2018 ◽  
Vol 05 (04) ◽  
pp. 1850041
Author(s):  
Suguru Yamanaka
Keyword(s):  
Risk Assessment ◽  
Credit Risk ◽  
Financial Institutions ◽  
High Frequency ◽  
Risk Model ◽  
Financial Statements ◽  
Order Information ◽  
Purchase Order ◽  
Credit Risk Assessment ◽  
Business Conditions

This paper proposes advanced credit risk assessment and lending operations using purchase order information from borrower firms. Purchase order information from a borrower firm is useful for financial institutions to evaluate the actual business conditions of the firm. This paper shows the application of purchase order information to lending operations and credit risk assessment, and reveals its effectiveness. First, we propose a “purchase order based” credit risk model for real-time credit risk monitoring of firms. Financial institutions can monitor the actual business conditions of borrower firms by evaluating the firm’s asset value using purchase order information. A combination of traditional firm monitoring using financial statements and high-frequency monitoring using purchase order information enables financial institutions to assess the business conditions of borrower firms more precisely and efficiently. Then, with high-frequency data, financial institutions can give borrower firms appropriate support if necessary on a timely basis. Second, we illustrate purchase order financing, which is the lending method backed by purchase order information from borrowers. With purchase order financing, firms that consistently receive purchase orders from credit-worthy firms can borrow money under more favorable lending terms than the usual lending terms based on the financial statements of the borrower firm.

Sign in / Sign up

Export Citation Format

Share Document