Article

A neural network model for credit risk evaluation.

Intelligent Systems Research Group, Near East University, Lefkosa, Mersin 10, Turkey.
International Journal of Neural Systems (Impact Factor: 6.06). 09/2009; 19(4):285-94. DOI: 10.1142/S0129065709002014
Source: PubMed

ABSTRACT Credit scoring is one of the key analytical techniques in credit risk evaluation which has been an active research area in financial risk management. This paper presents a credit risk evaluation system that uses a neural network model based on the back propagation learning algorithm. We train and implement the neural network to decide whether to approve or reject a credit application, using seven learning schemes and real world credit applications from the Australian credit approval datasets. A comparison of the system performance under the different learning schemes is provided, furthermore, we compare the performance of two neural networks; with one and two hidden layers following the ideal learning scheme. Experimental results suggest that neural networks can be effectively used in automatic processing of credit applications.

3 Followers
 · 
417 Views
  • [Show abstract] [Hide abstract]
    ABSTRACT: In poultry processing plants, the sorting of raw poultry portions into separate containers prior to packaging is performed mostly by human laborers. This sorting method has two problems: labor cost and health hazard due to possible contamination between raw meat and humans. Therefore, an automated sorting system is required to avoid these problems. In this article, we present an automatic portion identification system that uses image processing and a neural network to identify six different chicken portions that are usually preferred by consumers. The proposed rotational invariant system can identify the cut portions regardless of their orientation with an overall correct identification rate of 97.57%. Potentially, the output of the proposed identification system can be used to move robotic arms to physically separate the identified chicken portions into separate containers. PRACTICAL APPLICATIONSThis work contributes to the development of an automated sorting system for practical use in poultry processing plants. The presented intelligent identification system is the main part of such an automated system. We train the system in this work to recognize the main chicken portions; however, other portions and other poultry birds can also be identified upon including their portion images in the training phase. This work differs from existing systems, in that it relies totally on the shape and coarse texture of a portion, using images as input data, and discards information like weight or size of the portion. Another advantage is the elimination of the need for using many birds during the development of the system; in fact, training the system can be achieved using only one bird and its portions.
    Journal of Food Process Engineering 10/2012; 35(5). DOI:10.1111/j.1745-4530.2010.00621.x · 0.63 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: The ability to accurately predict business failure is a very important issue in financial decision-making. Incorrect decision-making in financial institutions is very likely to cause financial crises and distress. Bankruptcy prediction and credit scoring are two important problems facing financial decision support. As many related studies develop financial distress models by some machine learning techniques, more advanced machine learning techniques, such as classifier ensembles and hybrid classifiers, have not been fully assessed. The aim of this paper is to develop a novel hybrid financial distress model based on combining the clustering technique and classifier ensembles. In addition, single baseline classifiers, hybrid classifiers, and classifier ensembles are developed for comparisons. In particular, two clustering techniques, Self-Organizing Maps (SOMs) and k-means and three classification techniques, logistic regression, multilayer-perceptron (MLP) neural network, and decision trees, are used to develop these four different types of bankruptcy prediction models. As a result, 21 different models are compared in terms of average prediction accuracy and Type I & II errors. By using five related datasets, combining Self-Organizing Maps (SOMs) with MLP classifier ensembles performs the best, which provides higher predication accuracy and lower Type I & II errors.
    Information Fusion 03/2014; 16:46–58. DOI:10.1016/j.inffus.2011.12.001 · 3.47 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Three probabilistic neural network approaches are used for credit screening and bankruptcy prediction: a logistic regression neural network (LRNN), a probabilistic neural network (PNN) and a semi-supervised expectation maximization-based neural network. Using real-world bankruptcy prediction and credit screening datasets, we compare the three probabilistic approaches using various performance criteria of sensitivity, specificity, accuracy, decile lift and area under receiver operating characteristics (ROC) curves. The results of our experiments indicate that the PNN outperforms the other two techniques for decile lift and specificity performance metric. Using the area under ROC curve, we find that for bankruptcy prediction data the PNN outperforms the other two approaches when false positive rates (FPRs) are less than 40 %. LRNN outperforms the other two techniques for FPRs higher than 40 % for bankruptcy data. We observe that the LRNN results are very sensitive to the ratio of examples belonging to two classes in training data and there is a tendency to overfit training data. Copyright © 2012 John Wiley & Sons, Ltd.
    Intelligent Systems in Accounting Finance & Management 10/2011; 18(4). DOI:10.1002/isaf.331