Abstract
Credit scoring has become a very important issue due to the recent growth of the credit industry. As the first objective, this chapter provides an academic database of literature between and proposes a classification scheme to classify the articles. The second objective of this chapter is to suggest the employing of the Optimally Weighted Fuzzy K-Nearest Neighbor (OWFKNN) algorithm for credit scoring. To show the performance of this method, two real world datasets from UCI database are used. In classification task, the empirical results demonstrate that the OWFKNN outperforms the conventional KNN and fuzzy KNN methods and also other methods. In the predictive accuracy of probability of default, the OWFKNN also show the best performance among the other methods. The results in this chapter suggest that the OWFKNN approach is mostly effective in estimating default probabilities and is a promising method to the fields of classification.
Top2. Literature Survey
This paper presents a comprehensive review of literature related to application of data mining techniques in credit scoring published in academic journals between 2000 and 2010.
For doing this research, we searched online journal databases which some of them are referenced here. These databases include Science Direct; Scopus, Emerald, Springer, IEEE Explore, Jstore, John Wiley, Academic Search Premier. The searched Journals include Expert Systems with Applications, European Journal of Operational Research, Computers & Operations Research, Computer Engineering and Applications, Journal of Empirical Finance, Journal of Banking & Finance, Journal of Business Economics and Management, Mathematics and Economics, IEEE international conference papers.
Key Terms in this Chapter
Credit Risk: Possibility of loss from a borrower's default.
Data Analysis: Evaluating data with analytical and logical perceptive to survey each element of the data.
Data Mining: Extracting useful knowledge from a huge data using analytical techniques such as artificial intelligence techniques, neural networks, and advanced statistical tools.
Probability of Default: Degree of inevitability that a firm will go into failure to pay or a promised customer will not perform affording to the agreement.
Classification: Grouping of different objects into mutually exclusive classes.
Risk Management: Identifying, investigating, valuating, controlling, avoiding, minimizing, or eliminating offensive risks.