A Study on Forecasting Accuracy Improvement of Case Based Reasoning Approach Using Fuzzy Relation

퍼지 관계를 활용한 사례기반추론 예측 정확성 향상에 관한 연구

  • Lee, In-Ho (Dept. of the Accounting Information, Woongji Accounting & Tax College) ;
  • Shin, Kyung-Shik (College of Business Admin., Ewha Womans University)
  • 이인호 (웅지세무대학 회계정보과) ;
  • 신경식 (이화여자대학교 경영대학 경영학과)
  • Received : 2010.10.01
  • Accepted : 2010.11.05
  • Published : 2010.12.31

Abstract

In terms of business, forecasting is a work of what is expected to happen in the future to make managerial decisions and plans. Therefore, the accurate forecasting is very important for major managerial decision making and is the basis for making various strategies of business. But it is very difficult to make an unbiased and consistent estimate because of uncertainty and complexity in the future business environment. That is why we should use scientific forecasting model to support business decision making, and make an effort to minimize the model's forecasting error which is difference between observation and estimator. Nevertheless, minimizing the error is not an easy task. Case-based reasoning is a problem solving method that utilizes the past similar case to solve the current problem. To build the successful case-based reasoning models, retrieving the case not only the most similar case but also the most relevant case is very important. To retrieve the similar and relevant case from past cases, the measurement of similarities between cases is an important key factor. Especially, if the cases contain symbolic data, it is more difficult to measure the distances. The purpose of this study is to improve the forecasting accuracy of case-based reasoning approach using fuzzy relation and composition. Especially, two methods are adopted to measure the similarity between cases containing symbolic data. One is to deduct the similarity matrix following binary logic(the judgment of sameness between two symbolic data), the other is to deduct the similarity matrix following fuzzy relation and composition. This study is conducted in the following order; data gathering and preprocessing, model building and analysis, validation analysis, conclusion. First, in the progress of data gathering and preprocessing we collect data set including categorical dependent variables. Also, the data set gathered is cross-section data and independent variables of the data set include several qualitative variables expressed symbolic data. The research data consists of many financial ratios and the corresponding bond ratings of Korean companies. The ratings we employ in this study cover all bonds rated by one of the bond rating agencies in Korea. Our total sample includes 1,816 companies whose commercial papers have been rated in the period 1997~2000. Credit grades are defined as outputs and classified into 5 rating categories(A1, A2, A3, B, C) according to credit levels. Second, in the progress of model building and analysis we deduct the similarity matrix following binary logic and fuzzy composition to measure the similarity between cases containing symbolic data. In this process, the used types of fuzzy composition are max-min, max-product, max-average. And then, the analysis is carried out by case-based reasoning approach with the deducted similarity matrix. Third, in the progress of validation analysis we verify the validation of model through McNemar test based on hit ratio. Finally, we draw a conclusion from the study. As a result, the similarity measuring method using fuzzy relation and composition shows good forecasting performance compared to the similarity measuring method using binary logic for similarity measurement between two symbolic data. But the results of the analysis are not statistically significant in forecasting performance among the types of fuzzy composition. The contributions of this study are as follows. We propose another methodology that fuzzy relation and fuzzy composition could be applied for the similarity measurement between two symbolic data. That is the most important factor to build case-based reasoning model.

미래에 대한 정확한 예측은 경영자, 또는 기업이 수행하는 경영의사결정에 매우 중요한 역할을 한다. 예측만 정확하다면 경영의사결정의 질은 매우 높아질 수 있을 것이다. 하지만 점점 가속화되고 있는 경영 환경의 변화로 말미암아 미래 예측을 정확하게 하는 일은 점점 더 어려워지고 있다. 이에 기업에서는 정확한 예측을 위하여 전문가의 휴리스틱뿐만 아니라 과학적 예측모형을 함께 활용하여 예측의 성과를 높이는 노력을 해 오고 있다. 본 연구는 사례기반추론모형을 예측을 위한 기본 모형으로 설정하고, 데이터 간의 유사도 측정에 퍼지 관계의 개념을 적용함으로써 개선된 예측성과를 얻고자 하였다. 특히, 독립변수 중 기호 데이터 형식의 속성을 가지는 변수들간의 유사도를 측정하기 위해 이진논리의 개념(일치여부의 판단)과 퍼지 관계 및 합성의 개념을 이용하여 도출된 유사도 매트릭스를 사용하였다. 연구 결과, 기호 데이터 형식의 속성을 가지는 변수들 간의 유사도 측정에서 퍼지 관계 및 합성의 개념을 적용하는 방법이 이진논리의 개념을 적용하는 방법과 비교하여 더 우수한 예측정확성을 나타내었다. 그러나 유사도 측정을 위해 다양한 퍼지합성방법(Max-min 합성, Max-product 합성, Max-average 합성)을 적용하여 예측하는 경우에는 예측정확성 측면에서 퍼지 합성방법 간의 통계적인 차이는 유의하지 않았다. 본 연구는 사례기반추론 모형의 구축에서 가장 중요한 유사도 측정에 있어서 퍼지 관계 및 퍼지 합성의 개념을 적용함으로써 유사도 측정 및 적용 방법론을 제시하였다는데 의의가 있다.

Keywords

References

  1. Alliger, G. M., S. L. Feinzig and E. A. Janak, "Fuzzy Sets and Personnel Selection : Discussion and an Application", Journal of Occupational and Organization Psychology, Vol.66, No.2(1993), 163-169. https://doi.org/10.1111/j.2044-8325.1993.tb00525.x
  2. Amen, R. and P. Vomacka, "Case-based Reasoning As a Tool for Materials Selection", Materials and Design, Vol.22(2001), 353-358. https://doi.org/10.1016/S0261-3069(00)00105-9
  3. Barletta, R., "An Introduction to Case-based Reasoning", AI Expert, Vol.6, No.8(1991), 42-49.
  4. Brown, C. E. and U. G. Gupta, "Applying Casebased Reasoning to the Accounting Domain", Intelligent Systems in Accounting, Finance and Management, Vol.3(1994), 205-221.
  5. Burkhard, H. D., "Similarity and Distance in Casebased Reasoning", Foundamenta Informaticae, Vol.47(2001), 201-215.
  6. Dorsey, D. W. and M. D. Coovert, "Mathematical Modeling of Decision Making : A Soft and Fuzzy Approach to Capturing Hard Decision", Human Factors, Vol.45, No.1(2003), 117-135. https://doi.org/10.1518/hfes.45.1.117.27228
  7. Fang, S. C. and G. Li, "Solving Fuzzy Relations Equation with a Linear Objective Function", Fuzzy Sets and Systems, Vol.7 (1999), 89-101.
  8. Gardingen, D. and I. Watson, "A Web Based CBR System for Heating Ventilation and Air Conditioning Systems Sales Support", Knowledge-based Systems, Vol.12(1999), 207-214. https://doi.org/10.1016/S0950-7051(99)00017-9
  9. Ghodousian, A. and E. Khorram, "Fuzzy linear optimization in the presence of the fuzzy relation inequality constraints with max-min composition", Information Sciences, Vol.178(2008) 501-519. https://doi.org/10.1016/j.ins.2007.07.022
  10. Hsu, C., C. Chiu and P. L. Hsu, "Predicting Information Systems Outsourcing Success Using a Hierarchical Design of Case-based Reasoning", Expert Systems with Applications, Vol.26(2004), 435-441. https://doi.org/10.1016/j.eswa.2003.10.002
  11. Khorram, E. and R. Hassanzadeha, "Solving nonlinear optimization problems subjected to fuzzy relation equation constraints with max-average composition using a modified genetic algorithm", Computers and Industrial Engineering, Vol.55(2008), 1-14. https://doi.org/10.1016/j.cie.2007.11.011
  12. Khorram, E. and H. Zarei, "Multi-objective optimization problems with Fuzzy relation equation constraints regarding max-average composition", Mathematical and Computer Modelling, Vol.49(2009), 856-867. https://doi.org/10.1016/j.mcm.2008.10.018
  13. Kolodner, J. L. and W. Mark, "Case-based Reasoning", IEEE Expert, Vol.7, No.5(1992), 5-6. https://doi.org/10.1109/64.129277
  14. Kosko, B., Neural Networks and Fuzzy Systems, Prentice-Hall, Upper Saddle River, NJ., 1991.
  15. Li, L. L. X., "Knowledge-based Problem Solving : An Approach to Heath Assessment", Expert Systems with Applications, Vol.16 (1999), 33-42. https://doi.org/10.1016/S0957-4174(98)00026-8
  16. Li, J. and G. Hu, "A new algorithm for minimizing a linear objective function subject to a system of fuzzy relation equations with max-product composition", Fuzzy Information and Engineering, Vol.2(2010), 249-267. https://doi.org/10.1007/s12543-010-0048-3
  17. Lin. J., "On the relation between fuzzy max-Archimedean t-norm relational equations and the covering problem", Fuzzy Sets and Systems, Vol.160(2009), 2328-2344. https://doi.org/10.1016/j.fss.2009.01.012
  18. Loetamonphong, J. and S. Fang, "Optimization of Fuzzy Relation Equation with Maxproduct Composition", Fuzzy Sets and Systems, Vol.118(2001), 509-517. https://doi.org/10.1016/S0165-0114(98)00417-5
  19. Markowskii, A. V., "On the Relation between Equations with Max-product Composition and the Covering Problem", Fuzzy Seta and Systems, Vol.153(2005), 261-273. https://doi.org/10.1016/j.fss.2005.02.010
  20. McLachlan, G., Discriminant Analysis And Statistical Pattern Recognition, John Wiley and Sons Inc, New York, (2004).
  21. Pires, G. and Y. Hoshiau, "A Wheelchair Steered through Voice Commands and Assisted by a Reactive Fuzzy Logic Controller", Journal of Intelligent and Robotics Systems, Vol.34, No.3(2002), 301-314. https://doi.org/10.1023/A:1016363605613
  22. Riesbeck, C. K. and R. Schank, Inside Case-Based Reasoning, Lawrence Eribaum Associates, (1989).
  23. Ross, T. J., Fuzzy Logic with Engineering Applications, John Wiley, New York, (2004).
  24. Shin, K. S. and H. J. Kim, "Optimization of Symbolic Similarity by Genetic Algorithm for Case Based Approach to Corporate Bond Rating", The 9th Asia-Pacific Decision Science Institute Conference, July, Seoul, Korea, (2004).
  25. Suh, M. S., W. C. Jhee, Y. K. Ko and A. Lee, "A Case-based Expert System Approach for Quality Design", Expert Systems with Applications, Vol.15(1998), 181-190. https://doi.org/10.1016/S0957-4174(98)00022-0
  26. Wang, H. F., "A Multiple-objectives Mathematical Programming Problem with Fuzzy Relation Constraints", Journal of Multi-criteria Decision Analysis, Vol.4(1995), 23-35. https://doi.org/10.1002/mcda.4020040103
  27. Wang, Z., Z. Liu and X. Ai, "Case Representation and Similarity in High-speed Machining", International Journal of Machine Tools and Manufacture, Vol.43(2003), 1347-1353. https://doi.org/10.1016/S0890-6955(03)00152-4
  28. Watson, I., Applying Case-Based Reasoning : Techniques for Enterprise Systems, Morgan Kaufman Publishers, San Francisco, CA., (1997).
  29. Wu, Y., C. Liu, Y. Lur and S. Guu, "One Simple Procedure to Finding the Best Approximate Solution for a Particular Fuzzy Relational Equation with Max-min Composition", Computational Science and Optimization, Third International Joint Conference(2010), 141-144.
  30. Zadeh, L. A., "The Concept of a Linguistic Variable and its Application to Approximate Reasoning-I", Information Sciences, Vol.8 (1975a), 199-249. https://doi.org/10.1016/0020-0255(75)90036-5
  31. Zadeh, L. A., "The Concept of a Linguistic Variable and its Application to Approximate Reasoning-II", Information Sciences, Vol.8 (1975b), 301-357. https://doi.org/10.1016/0020-0255(75)90046-8
  32. Zadeh, L. A., "The Concept of a Linguistic Variable and its Application to Approximate Reasoning-III", Information Sciences, Vol.9 (1975c), 43-80. https://doi.org/10.1016/0020-0255(75)90017-1
  33. Zadeh, L. A., "Fuzzy Sets as a Basis for a Theory of Possibility", Fuzzy Sets and Systems, Vol.1(1978), 3-28. https://doi.org/10.1016/0165-0114(78)90029-5