Balancing the trade-off between accuracy and interpretability in software defect prediction



Classification techniques of supervised machine learning have been successfully applied to various domains of practice. When building a predictive model, there are two important criteria: predictive accuracy and interpretability, which generally have a trade-off relationship. In particular, interpretability should be accorded greater emphasis in the domains where the incorporation of expert knowledge into a predictive model is required.


The aim of this research is to propose a new classification model, called superposed naive Bayes (SNB), which transforms a naive Bayes ensemble into a simple naive Bayes model by linear approximation.


In order to evaluate the predictive accuracy and interpretability of the proposed method, we conducted a comparative study using well-known classification techniques such as rule-based learners, decision trees, regression models, support vector machines, neural networks, Bayesian learners, and ensemble learners, over 13 real-world public datasets.


A trade-off analysis between the accuracy and interpretability of different classification techniques was performed with a scatter plot comparing relative ranks of accuracy with those of interpretability. The experiment results show that the proposed method (SNB) can produce a balanced output that satisfies both accuracy and interpretability criteria.


SNB offers a comprehensible predictive model based on a simple and transparent model structure, which can provide an effective way for balancing the trade-off between accuracy and interpretability.

This is a preview of subscription content, log in to check access.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9


  1. Agterberg FP, Bonham-Carter GF, Wright DF (1990) Statistical pattern integration for mineral exploration. Computer Applications in Resource Estimation Prediction and Assessment for Metals and Petroleum, pp 1–21

  2. Akaike H (1973) Information theory and an extension of the maximum likelihood principle. In: Second international symposium on information theory, pp 267–281

  3. Allahyari H, Lavesson N (2011) User-oriented assessment of classification model understandability. In: 11th Scandinavian conference on artificial intelligence, pp 11–19

  4. Aly M (2005) Survey on multiclass classification methods. Neural Netw 19:1–9

    Google Scholar 

  5. Bauer E, Kohavi R (1999) An empirical comparison of voting classification algorithms: bagging, boosting, and variants. Mach Learn 36(1-2):105–139

    Article  Google Scholar 

  6. Bishop CM (2006) Pattern recognition and machine learning. Springer

  7. Bonham-Carter GF, Agterberg FP, Wright DF (1988) Integration of geological datasets for gold exploration in Nova Scotia. Digital Geologic and Geographic Information Systems, pp 15–23

  8. Bouckaert RR (2004) Naive bayes classifiers that perform well with continuous variables. In: Australasian joint conference on artificial intelligence, pp 1089–1094

  9. Breiman L (1996) Bagging predictors. Mach Learn 24(2):123–140

    MATH  MathSciNet  Google Scholar 

  10. Breiman L (2001) Random forests. Mach Learn 45(1):5–32

    MATH  Article  Google Scholar 

  11. Briand LC, Basili VR, Thomas WM (1992) A pattern recognition approach for software engineering data analysis. IEEE Trans Softw Eng 18(11):931–942

    Article  Google Scholar 

  12. Burges CJC (1998) A tutorial on support vector machines for pattern recognition. Data Min Knowl Disc 2(2):121–167

    Article  Google Scholar 

  13. Bury H, Wagner D (2008) Group judgement with ties. Distance-based methods. In: Aschemann H (ed) New approaches in automation and robotics. IntechOpen, London, pp 153–172

    Google Scholar 

  14. Carranza EJM (2004) Weights of evidence modeling of mineral potential: a case study using small number of prospects, Abra, Philippines. Nat Resour Res 13(3):173–187

    Article  Google Scholar 

  15. Cestnik B (1990) Estimating probabilities: a crucial task in machine learning. In: Proceedings of the 9th European conference on artificial intelligence, ECAI '90, pp 147–149

  16. Choetkiertikul M, Dam HK, Tran T, Ghose A (2015) Characterization and prediction of issue-related risks in software projects. In: Proceedings of the 12th working conference on mining software repositories, pp 280–291

  17. Cohen WW (1995) Fast effective rule induction. In: Proceedings of the twelfth international conference on machine learning, ICML’95, pp 115–123

  18. Dahal RK, Hasegawa S, Nonomura A, Yamanaka M, Masuda T, Nishino K (2008) GIS-based weights-of-evidence modelling of rainfall-induced landslides in small catchments for landslide susceptibility mapping. Environ Geol 54(2):311–324

    Article  Google Scholar 

  19. Dejaeger K, Verbeke W, Martens D, Baesens B (2012) Data mining techniques for software effort estimation: a comparative study. IEEE Trans Softw Eng 38(2):375–397

    Article  Google Scholar 

  20. Dejaeger K, Verbraken T, Baesens B (2013) Toward comprehensible software fault prediction models using bayesian network classifiers. IEEE Trans Softw Eng 39(2):237–257

    Article  Google Scholar 

  21. Domingos P, Pazzani M (1997) On the optimality of the simple Bayesian classifier under zero-one loss. Mach Learn 29(2):103–130

    MATH  Article  Google Scholar 

  22. Fawcett T (2006) An introduction to ROC analysis. Pattern Recogn Lett 27(8):861–874

    MathSciNet  Article  Google Scholar 

  23. Fayyad U, Irani K (1993) Multi-interval discretization of continuous-valued attributes for classification learning. In: Proceedings of the 13th international joint conference on artificial intelligence, IJCAI’93, pp 1022–1029

  24. Fayyad U, Piatetsky-Shapiro G, Smyth P (1996) From data mining to knowledge discovery in databases. AI Mag 17(3):37–54

    Google Scholar 

  25. Fenton NE, Neil M (1999) A critique of software defect prediction models. IEEE Trans Softw Eng 25(5):675–689

    Article  Google Scholar 

  26. Fenton N, Neil M, Marsh W, Hearty P, Radliński Ł, Krause P (2008) On the effectiveness of early life cycle defect prediction with Bayesian nets. Empir Softw Eng 13(5):499–537

    Article  Google Scholar 

  27. Freitas AA (2004) A critical review of multi-objective optimization in data mining: a position paper. ACM SIGKDD Explorations Newsletter 6(2):77–86

    Article  Google Scholar 

  28. Freitas AA (2014) Comprehensible classification models: a position paper. ACM SIGKDD Explorations Newsletter 15(1):1–10

    Article  Google Scholar 

  29. Freund Y, Schapire RE (1997) A decision-theoretic generalization of on-line learning and an application to boosting. J Comput Syst Sci 55(1):119–139

    MathSciNet  MATH  Article  Google Scholar 

  30. Friedman JH (2001) Greedy function approximation: a gradient boosting machine. Ann Stat 29(5):1189–1232

    MathSciNet  MATH  Article  Google Scholar 

  31. Friedman JH (2002) Stochastic gradient boosting. Comput Stat Data Anal 38(4):367–378

    MathSciNet  MATH  Article  Google Scholar 

  32. Friedman N, Geiger D, Goldszmidt M (1997) Bayesian network classifiers. Mach Learn 29(2-3):131–163

    MATH  Article  Google Scholar 

  33. Ghotra B, McIntosh S, Hassan AE (2015) Revisiting the impact of classification techniques on the performance of defect prediction models. In: Proceedings of the 37th international conference on software engineering. ICSE’15, pp 789–800

  34. Goldstein A, Kapelner A, Bleich J, Pitkin E (2015) Peeking inside the black box: Visualizing statistical learning with plots of individual conditional expectation. J Comput Graph Stat 24(1):44–65

    MathSciNet  Article  Google Scholar 

  35. Good IJ (1985) Weight of evidence: a brief survey. In: Bernardo JM, DeGroot MH, Lindley DV, Smith AFM (eds) Bayesian Statistics 2: Proceedings of the second valencia international meeting: September 6/10, 1983, New York: North Holland, pp 249–269 (including discussion)

  36. Goodman SN (1999) Toward evidence-based medical statistics. 2: the Bayes factor. Ann Intern Med 130(12):1005–1013

    Article  Google Scholar 

  37. Guo L, Ma Y, Cukic B, Singh H (2004) Robust prediction of fault-proneness by random forests. In: IEEE 15th international symposium on software reliability engineering, ISSRE, pp 417–428

  38. Hall T, Beecham S, Bowes D, Gray D, Counsell S (2012) A systematic literature review on fault prediction performance in software engineering. IEEE Trans Softw Eng 38(6):1276–1304

    Article  Google Scholar 

  39. Halstead MH (1977) Elements of software science. Elsevier

  40. Hastie T, Tibshirani R, Friedman J (2009) The elements of statistical learning, 2nd edn. Springer

  41. Heckerman DE, Horvitz EJ, Nathwani BN (1991) Toward normative expert systems: the Pathfinder project. Methods Inf Med 31(2):90–105

    Google Scholar 

  42. Holte RC (1993) Very simple classification rules perform well on most commonly used datasets. Mach Learn 11(1):63–90

    MathSciNet  MATH  Article  Google Scholar 

  43. Hu Y, Zhang X, Ngai EWT, Cai R, Liu M (2013) Software project risk analysis using Bayesian networks with causality constraints. Decis Support Syst 56:439–449

    Article  Google Scholar 

  44. Huysmans J, Dejaeger K, Mues C, Vanthienen J, Baesens B (2011) An empirical evaluation of the comprehensibility of decision table, tree and rule based predictive models. Decis Support Syst 51(1):141–154

    Article  Google Scholar 

  45. Jain AK, Mao J, Mohiuddin KM (1996) Artificial neural networks: a tutorial. IEEE Comput 29(3):31–44

    Article  Google Scholar 

  46. Jelihovschi E, Faria JC, Allaman IB (2014) ScottKnott: a package for performing the Scott-Knott clustering algorithm in R. Trends in Applied and Computational Mathematics 15(1):003–017

    MathSciNet  Google Scholar 

  47. Jiang Y, Cukic B, Ma Y (2008a) Techniques for evaluating fault prediction models. Empir Softw Eng 13(5):561–595

    Article  Google Scholar 

  48. Jiang Y, Cukic B, Menzies T, Bartlow N (2008b) Comparing design and code metrics for software quality prediction. In: Proceedings of the 4th international workshop on Predictor models in software engineering, pp 11–18

  49. Jiang L, Zhang H, Cai Z (2009) A novel Bayes model: hidden naive Bayes. IEEE Trans Knowl Data Eng 21(10):1361–1371

    Article  Google Scholar 

  50. John GH, Langley P (1995) Estimating continuous distributions in Bayesian classifiers. In: Proceedings of the 11th conference on uncertainty in artificial intelligence, pp 338–345

  51. Kamei Y, Shihab E (2016) Defect prediction: accomplishments and future challenges. In: 23rd International conference on software analysis, evolution, and reengineering, SANER, vol 5, pp 33–45

  52. Kamei Y, Shihab E, Adams B, Hassan AE, Mockus A, Sinha A, Ubayashi N (2013) A large-scale empirical study of just-in-time quality assurance. IEEE Trans Softw Eng 39(6):757–773

    Article  Google Scholar 

  53. Kim S, Whitehead EJ Jr, Zhang Y (2008) Classifying software changes: clean or buggy? IEEE Trans Softw Eng 34(2):181–196

    Article  Google Scholar 

  54. Kohavi R (1996) Scaling up the accuracy of Naive-Bayes classifiers: a decision-tree hybrid. In: Proceedings of the 2nd international conference on knowledge discovery and data mining. KDD96, pp 202–207

  55. Kononenko I (1993) Inductive and Bayesian learning in medical diagnosis. Appl Artif Intell 7(4):317–337

    Article  Google Scholar 

  56. Kotsiantis SB, Zaharakis I, Pintelas P (2007) Supervised machine learning: a review of classification techniques. Informatica 31:249–268

    MathSciNet  Google Scholar 

  57. Kulesza T, Burnett M, Wong WK, Stumpf S (2015) Principles of explanatory debugging to personalize interactive machine learning. In: Proceedings of the 20th International Conference on Intelligent User Interfaces, pp 126–137

  58. Le Cessie S, Van Houwelingen JC (1992) Ridge estimators in logistic regression. Appl Stat 191–201

  59. Lessmann S, Baesens B, Mues C, Pietsch S (2008) Benchmarking classification models for software defect prediction: a proposed framework and novel findings. IEEE Trans Softw Eng 34(4):485–496

    Article  Google Scholar 

  60. Lewis DD (1998) Naive (Bayes) at forty: the independence assumption in information retrieval. In: European conference on machine learning, pp 4–15

  61. Lipton ZC (2016) The mythos of model interpretability. In: 2016 ICML workshop on human interpretability in machine learning. WHI 2016

  62. Madigan D, Mosurski K, Almond RG (1997) Graphical explanation in belief networks. J Comput Graph Stat 6(2):160–181

    Google Scholar 

  63. Malhotra R (2015) A systematic review of machine learning techniques for software fault prediction. Appl Soft Comput 27:504–518

    Article  Google Scholar 

  64. Martens D, Vanthienen J, Verbeke W, Baesens B (2011) Performance of classification models from a user perspective. Decis Support Syst 51(4):782–793

    Article  Google Scholar 

  65. McCabe TJ (1976) A complexity measure. IEEE Trans Softw Eng 2(4):308–320

    MathSciNet  MATH  Article  Google Scholar 

  66. Menzies T, Greenwald J, Frank A (2007) Data mining static code attributes to learn defect predictors. IEEE Trans Softw Eng 33(1):2–13

    Article  Google Scholar 

  67. Menzies T, Krishna R, Pryor D (2016) The Promise Repository of Empirical Software Engineering Data; North Carolina State University, Department of Computer Science bibtex

  68. Mori T (2015) Superposed Naive Bayes for Accurate and Interpretable Prediction. In: Proceedings of the 14th IEEE international conference on machine learning and applications. ICMLA 2015, pp 1228–1233

  69. Mori T, Tamura S, Kakui S (2013) Incremental estimation of project failure risk with Naive Bayes classifier. In: Proceedings of 7th ACM/IEEE international symposium on empirical software engineering and measurement. ESEM 2013, pp 283–286

  70. Platt JC (1999) Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. Advances in Large Margin Classifiers, 10(3):61–74

  71. Quinlan JR (1993) C4.5: programs for machine learning. Morgan Kaufmann, San Mateo

    Google Scholar 

  72. Ribeiro MT, Singh S, Guestrin C (2016) Why should I trust you?: Explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pp 1135–1144

  73. Ridgeway G, Madigan D, Richardson T, O'Kane J (1998) Interpretable boosted Naive Bayes classification. In: Proceedings of the 4th international conference on knowledge discovery and data mining. KDD98, pp 101–104

  74. Rish I (2001) An empirical study of the naive Bayes classifier. In: IJCAI 2001 workshop on empirical methods in artificial intelligence, 3(22):41–46

  75. Saaty TL (1990) How to make a decision: the analytic hierarchy process. Eur J Oper Res 48(1):9–26

    MathSciNet  MATH  Article  Google Scholar 

  76. Sakamoto Y, Akaike H (1978) Analysis of cross classified data by AIC. Ann Inst Stat Math 30(1):185–197

    MathSciNet  MATH  Article  Google Scholar 

  77. Schwarz G (1978) Estimating the dimension of a model. Ann Stat 6(2):461–464

    MathSciNet  MATH  Article  Google Scholar 

  78. Shepperd M, Song Q, Sun Z, Mair C (2013) Data quality: some comments on the NASA software defect datasets. IEEE Trans Softw Eng 39(9):1208–1215

    Article  Google Scholar 

  79. Spiegelhalter DJ, Knill-Jones RP (1984) Statistical and knowledge-based approaches to clinical decision-support systems, with an application in gastroenterology. Journal of the Royal Statistical Society. Series A (General):35–77

  80. Vandecruys O, Martens D, Baesens B, Mues C, De Backer M, Haesen R (2008) Mining software repositories for comprehensible software fault prediction models. J Syst Softw 81(5):823–839

    Article  Google Scholar 

  81. Webb GI (2000) Multiboosting: a technique for combining boosting and wagging. Mach Learn 40(2):159–196

    Article  Google Scholar 

  82. Webb GI, Boughton JR, Wang Z (2005) Not so naive Bayes: aggregating one-dependence estimators. Mach Learn 58(1):5–24

    MATH  Article  Google Scholar 

  83. Wen J, Li S, Lin Z, Hu Y, Huang C (2012) Systematic literature review of machine learning based software development effort estimation models. Inf Softw Technol 54(1):41–59

    Article  Google Scholar 

  84. Witten IH, Frank E, Hall MA, Pal CJ (2011) Data mining: practical machine learning tools and techniques, 3rd edn. Morgan Kaufmann

  85. Yang Y, Webb GI (2009) Discretization for naive-Bayes learning: managing discretization bias and variance. Mach Learn 74(1):39–74

    Article  Google Scholar 

  86. Zadrozny B, Elkan C (2002) Transforming classifier scores into accurate multiclass probability estimates. In: Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining, pp 694–699

  87. Zhang H (2004) The optimality of naive Bayes. In: Proceedings of the 17th Florida artificial intelligence research society conference. FLAIRS2004, pp 562–567

  88. Zimmermann T, Premraj R, Zeller A (2007) Predicting defects for eclipse. In: Proceedings of the third international workshop on predictor models in software engineering, IEEE Computer Society, pp 9

  89. Zimmermann T, Nagappan N, Gall H, Giger E, Murphy B (2009) Cross-project defect prediction: a large scale experiment on data vs. domain vs. process. In: Proceedings of the the 7th joint meeting of the European software engineering conference and the ACM SIGSOFT symposium on The foundations of software engineering, pp 91–100

Download references


The authors would like to thank Prof. William Riley Holden of Japan Advanced Institute of Science and Technology (JAIST) for his helpful comments and advice on the manuscript. The authors also would like to thank the anonymous reviewers who gave us invaluable suggestions.

Author information



Corresponding author

Correspondence to Toshiki Mori.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Communicated by: Tim Menzies


Appendix 1

The AIC for the contingency table of Table 1 is derived as follows (Sakamoto and Akaike 1978):

$$ {AIC}_1^{(i)}=\left(-2\right)\sum \limits_{1\le y\le 2}\sum \limits_{1\le x\le k}\left\{{n}_{\left(i,y,x\right)}\log \left({n}_{\left(i,y,x\right)}/{n}_{\left(i,\ast, \ast \right)}\right)\right\}+2\left(2k-1\right) $$

If mutual independence between Y and Xi is assumed, the AIC changes like the following:

$$ {AIC}_0^{(i)}=\left(-2\right)\sum \limits_{1\le y\le 2}\sum \limits_{1\le x\le k}\left\{{n}_{\left(i,y,x\right)}\log \left({n}_{\left(i,y,\ast \right)}{n}_{\left(i,\ast, x\right)}/{n}_{\left(i,\ast, \ast \right)}^2\right)\right\}+2k $$

The difference between the AIC of the dependence model (\( {AIC}_1^{(i)} \)) and that of the independence model (\( {AIC}_0^{(i)} \)) is given by

$$ {\displaystyle \begin{array}{l}\ \varDelta {AIC}^{(i)}={AIC}_1^{(i)}-{AIC}_0^{(i)}\\ {}=\left(-2\right)\sum \limits_{1\le y\le 2}\sum \limits_{1\le x\le k}\left\{{n}_{\left(i,y,x\right)}\log \frac{n_{\left(i,\ast, \ast \right)}{n}_{\left(i,y,x\right)}}{n_{\left(i,y,\ast \right)}{n}_{\left(i,\ast, x\right)}}\right\}+2\left(k-1\right)\ \end{array}} $$

Similarly to the MDL criterion (Fayyad and Irani 1993), the discretization method using AIC starts with a single interval containing all data, and recursively splits intervals. If ΔAIC(i) is greater than a given (negative) threshold, the independence model will be selected as a model with a smaller AIC, so that no more splitting is needed. The total sum of ΔAIC(i) for all the splittings is AIC(i), the reversal of which indicates the importance of the variable Xi. The variables that have positive AIC can be ignored, because the AIC of a single interval variable is equal to zero, as derived from Eq. 11.

The discretization process using BIC is almost same as that based on AIC. ΔBIC(i), i.e., the difference between the BIC of a dependence model (\( {BIC}_1^{(i)} \)) and that of a independence model (\( {BIC}_0^{(i)} \)), is obtained by simply replacing the last term 2(k − 1) in Eq. 13 with logn(k − 1), where n is the number of instances.

$$ {\displaystyle \begin{array}{l}\ \varDelta {BIC}^{(i)}={BIC}_1^{(i)}-{BIC}_0^{(i)}\\ {}=\left(-2\right)\sum \limits_{1\le y\le 2}\sum \limits_{1\le x\le k}\left\{{n}_{\left(i,y,x\right)}\log \frac{n_{\left(i,\ast, \ast \right)}{n}_{\left(i,y,x\right)}}{n_{\left(i,y,\ast \right)}{n}_{\left(i,\ast, x\right)}}\right\}+\log n\left(k-1\right)\end{array}} $$

The total sum of ΔBIC(i) for all the splittings is BIC(i), the reversal of which indicates the importance of the variable Xi.

Appendix 2

Abbr. Parameter Settings in Weka machine learning toolkit
OneR OneR -B 6
JRip JRip -F 3 -N 2.0 -O 2 -S 1
J48 J48 -C 0.25 -M 2
NBTree NBTree
LR Logistic -R 1.0E-8 -M -1
SVM SMO -C 1.0 -L 0.001 -P 1.0E-12 -N 0 -M -V -1 -W 1
-K “weka.classifiers.functions.supportVector.PolyKernel -C 250007 -E 1.0”
MLP MultilayerPerceptron -L 0.3 -M 0.2 -N 500 -V 0 -S 0 -E 20 -H a
NBc NaiveBayes
NBd NaiveBayes –D
TAN BayesNet -D -Q --
-S BAYES -E SimpleEstimator -- -A 0.5
AODE FilteredClassifier -F “weka.filter.supervised.attribute.Discretize -R first-last”
-W weka.classifiers.bayes.AODE -- -F 1
HNB FilteredClassifier -F “weka.filter.supervised.attribute.Discretize -R first-last”
-W weka.classifiers.bayes.HNB
AdaBst AdaBoostM1 -P 100 -S 1 -I 100 -W weka.classifiers.trees.DecisionStump
RF RandomForest -I 100 -K 0 -S 1

Appendix 3

Dataset Random Seeds used in Weka
1st CV 2nd CV 3rd CV 4th CV 5th CV
MC2 869 280 820 326 961
KC3 309 433 717 708 321
MW1 154 509 564 850 493
CM1 325 629 602 391 467
PC1 111 501 663 151 200
PC2 474 303 537 936 614
PC3 298 566 445 44 381
PC4 711 652 811 516 832
PC5 543 569 505 684 978
MC1 292 604 61 154 746
JM1 172 283 92 966 398
Bugzilla 559 776 599 493 383
Columba 782 155 941 517 882

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Mori, T., Uchihira, N. Balancing the trade-off between accuracy and interpretability in software defect prediction. Empir Software Eng 24, 779–825 (2019).

Download citation


  • Software defect prediction
  • Predictive accuracy
  • Interpretability
  • Trade-off analysis
  • Naive Bayes classifier
  • Weights of evidence
  • Ensemble learning
  • Model approximation