Browse > Article

Estimating Software Development Cost using Support Vector Regression  

Park, Chan-Kyoo (동국대학교 경영학과)
Publication Information
Korean Management Science Review / v.23, no.2, 2006 , pp. 75-91 More about this Journal
Abstract
The purpose of this paper is to propose a new software development cost estimation method using SVR(Support Vector Regression) SVR, one of machine learning techniques, has been attracting much attention for its theoretic clearness and food performance over other machine learning techniques. This paper may be the first study in which SVR is applied to the field of software cost estimation. To derive the new method, we analyze historical cost data including both well-known overseas and domestic software projects, and define cost drivers affecting software cost. Then, the SVR model is trained using the historical data and its estimation accuracy is compared with that of the linear regression model. Experimental results show that the SVR model produces more accurate prediction than the linear regression model.
Keywords
Software Cost Estimation; Support Vector Regression; Machine Learning;
Citations & Related Records
Times Cited By KSCI : 1  (Citation Analysis)
연도 인용수 순위
1 박찬규, 신수정, 이현옥, '국내 소프트웨어개발사업에 적합한 기능점수규모 예측방법에 관한 연구', '경영과학', 제20권, 제2호(2003), pp.179-196
2 IFPUG, Function Point Counting Practices Manual(Release 4.2), International Function Point Users Group, 2000
3 ISBSG, Practical project estimation：A tool kit for estimating software development effort and duration, International Software Benchmarking Standards Group, 2001
4 Kitchenham, B.A. and S.L. Pfleeger, 'Software quality：The elusive target,' IEEE Software, Vol.13(1996), pp.12-21   DOI   ScienceOn
5 Luntz, A. and V. Brailovsky, 'On estimation of characters obtained in statistical procedure of recognition,' Technicheskaya Kibernetica, Vol.3(1969)
6 Porter, A. and R. Selby, 'Empirically-guided software development using metricbased classification trees,' IEEE Software, Vol.7(1990), pp.46-54
7 Software Productivity Research, http://www.spr.com
8 이양규, '기능점수모형을 이용한 소프트웨어 개발비용 산정', '경영연구', 제6권(1997), pp. 241-261
9 Cristianini, N. and J. Shawe-Taylor, An introduction to support vector machines and other kernel-based learning methods, Cambridge University Press, 2000
10 Schoelkopf, B. and A.J. Smola, Learning with Kernels：Support Vector Machines, Regularization, Optimization, and Beyond, MIT Press, 2002
11 Pfleeger, S.L., Software Engineering Theory and Practice 2nd ed., Prentice Hall, 2001
12 Price Systems, http://www.pricesystems.com
13 김현수, '기능점수를 이용한 소프트웨어 규모 및 비용산정 방안에 관한 연구', '경영과학', 제14권, 제1호(1997), pp.131-149
14 Vapnik, V., Statistical Learning Theory, Wiley, 1998
15 김우제, 박찬규, 신수정, 'AHP를 이용한 소프트웨어개발비 보정계수 산정', 'IE Interfaces', 제17권, 제5호(2005), pp.1-11
16 Jones, T.C., Estimating Software Costs, McGraw-Hill, 1998
17 Sommerville, I., Software Engineering 6th ed., Addison-Wesley, 2001
18 Finnie, G.R., G.E. Witting, and J-M. Desharnais, 'A comparision of software effort estimation techniques：Using function points with neural networks, case-based reasoning and regression models,' Journal of Systems Software, Vol.39(1997), pp.281-289   DOI   ScienceOn
19 박찬규, 구자환, 김성희, 신수정, 송병선, '공공부문 정보화사업의 소프트웨어 개발비용 예측에 관한 연구', '경영과학', 제19권, 제2호(2002), pp.191-204
20 Srinivasan, K. and D. Fisher, 'Machine learning approaches to estimating development effort,' IEEE Transactions on Software Engineering, Vol.21(1995), pp.126-137   DOI   ScienceOn
21 Chang, C.-C. and C.-J. Lin, LIBSVM：a library for support vector machines, http://www.csie.ntu.edu.tw/~cjlin/libsvm, 2001
22 Vidger, M.R. and A.W. Kark, Software cost estimation and control, Institute for Information Technology, National Research Council Canada, 1994
23 Boehm, B.-W. et al., Software cost estimation with COCOMO II, Prentice Hall PTR, 2000
24 Shepperd, M., 'Effort and size estimation： An appraisal,' Software Reliability and Metrics Club Newsletter, January：6-8 (1997), London, Centre for Software Reliability