Software Defect Prediction is one of the important research areas of the software engineering. When developing new software from the existing prototype a software defect handling is one the major factor. In order to improve the quality of the software various data mining techniques are being used and applied to obtain predictions regarding the failure of particular software component by using the past datasets or logs consisting of various software measures related to the software defects. The main objective of the research was to rank & identify the most appropriate data mining classifier algorithms from the fifteen selected algorithms such as Lazy-IBK, Lazy-K Star, Function-SMO, Function-Multilayer Perceptron,Rules-ZeroR,Rules-OneR,Rules-PART,Tree-REP,Tree-Decision stump, J48, Naïve Bayes, BayesNet, Meta- AdaBoostM1,Misc-HyperPipes & Misc-VFI. In this particular research study firstly, 15 classifiers were applied to four datasets and the classification results were measured using 12 performance measures. Second, five MCDM methods (i.e., TOPSIS, GRA, VIKOR, PROMETHEE II, and ELECTRE III) were used to rank the classification algorithms based on their performances. So finally it can be concluded that the TOPSIS & VIKOR shows strong negative correlation which depicts that there is association between the two sets and the results were found in accordance. The best algorithm for software defect prediction datasets was found to be Lazy-IBK with highest overall score of 0.8023.

J48, IBK, TOPSIS, VIKOR, GRA, PROMETHEE II and ELECTRE III

[1] Akmel, Feidu & Birihanu, Ermiyas & Siraj, Bahir. (2018). “A Literature Review Study of Software Defect Prediction using Machine Learning Techniques”. International Journal of Emerging Research in Management and Technology. 6. 300. 10.23956/ijermt.v6i6.286.
[2] He, Peng, et al. "An empirical study on software defect prediction with a simplified metric set." Information and Software Technology 59 (2015): 170-190.
[3] Amit Kumar Jakhar, K. R. (2018). “Software Fault Prediction with Data Mining Techniques by Using”. International Journal on Electrical Engineering and Informatics - Volume 10, Number 3 , 447-465.
[4] Balogun, Abdullateef & O Bajeh, Amos & A Orie, Victor & W Yusuf-Asaju, Ayisat. (2018). “Software Defect Prediction Using Ensemble Learning: An ANP Based Evaluation Method”.
[5] Hammouri, Awni & Hammad, Mustafa & Alnabhan, Mohammad & Alsarayrah, Fatima. (2018). “Software Bug Prediction using Machine Learning Approach”. International Journal of Advanced Computer Science and Applications Vol. 9, No. 2,78-83.
[6] Deep Singh, Praman & Chug, Anuradha.(2017). “Software defect prediction analysis using machine learning algorithms”. 775-781. 10.1109/CONFLUENCE.2017.7943255.
[7] A.Parameswari. (2015). “Comparing Data Mining Techniques For Software Defect Prediction”. International Journal of Science and Engineering Research (IJ0SER),Vol 3 Issue 5 , 3221 5687, (P) 3221 568X.
[8] Saiqa A, Luiz F, and F. A, "Benchmarking Machine Learning Techniques for Software Defect Detection". International Journal of Software Engineering & Applications, vol. 6, pp. 11-23, May 2015.
[9] Dwivedi, V.K., & Singh, M.K. (2016). “Software Defect Prediction Using Data Mining Classification Approach”.
[10] Gang Kou, Y. L. (2012). “Evaluation of Classification Algorithms Using MCDM And Rank Correlation”. International Journal of Information Technology & Decision Making Vol. 11, No. 1 , 197-225.
[11] Ayse Tosun (2009) . AR1/Software defect prediction.The PROMISE Repository of Software Engineering Databases. School of Information Technology and Engineering, University of Ottawa, Canada . Creator : Software Research Laboratory (Softlab), Bogazici University, Istanbul, Turkey .Available: http://promise.site.uottawa.ca/SERepository.
[12] Tim Menzies (2004). CM1/Software defect prediction.The PROMISE Repository of Software Engineering Databases. School of Information Technology and Engineering, University of Ottawa, Canada . Creator : NASA. Available: http://promise.site.uottawa.ca/SERepository.
[13] Tim Menzies (2004). JM1/Software defect prediction. The PROMISE Repository of Software Engineering Databases. School of Information Technology and Engineering, University of Ottawa, Canada . Creator : NASA.Available: http://promise.site.uottawa.ca/SERepository.
[14] Tim Menzies (2004). KC1/Software defect prediction. The PROMISE Repository of Software Engineering Databases. School of Information Technology and Engineering, University of Ottawa, Canada .Creator : NASA.Available: http://promise.site.uottawa.ca/SERepository.