Software maintainability prediction using an enhanced random forest algorithm

Abstract Now-a-days, software maintainability has become one of the significant quality-assessing attributes for any software system. Current study presents an enhanced-RFA (Random Forest Algorithm) approach for Software Maintainability Prediction. The proposed approach combines Random Forest (RF) algorithm with three prevalent feature selection techniques namely Chi-Squared, RF and Linear Correlation Filter along with a re-sampling technique intended to improve the prediction accuracy of basic RF algorithm. Enhanced- RFA is applied on two commercially available datasets, QUES and UIMS and performance is evaluated on the basis of R2. Results indicate that the proposed approach performs significantly better than RFA for both the datasets with an improvement in R2 values equal to 69.50%, 65.57% & 69.40% for QUES and 31.90%, 44.94% & 51.81% for UIMS using chisquared, RF and linear correlation filter techniques respectively.

[1]  Ruchika Malhotra,et al.  Software Maintainability Prediction using Machine Learning Algorithms , 2012 .

[2]  Ruchika Malhotra,et al.  Application of Evolutionary Algorithms for Software Maintainability Prediction using Object-Oriented Metrics , 2014, BICT.

[3]  Anuradha Chug,et al.  Software Maintainability: Systematic Literature Review and Current Trends , 2016, Int. J. Softw. Eng. Knowl. Eng..

[4]  Moataz A. Ahmed,et al.  Machine learning approaches for predicting software maintainability: a fuzzy-based transparent model , 2013, IET Softw..

[5]  Lov Kumar,et al.  Software maintainability prediction using hybrid neural network and fuzzy logic approach with parallel computing concept , 2017, Int. J. Syst. Assur. Eng. Manag..

[6]  Irfan Ahmad,et al.  Three empirical studies on predicting software maintainability using ensemble methods , 2015, Soft Comput..

[7]  Stephen G. MacDonell,et al.  Assessing prediction systems , 1999 .

[8]  Dan X. Houston,et al.  COST OF SOFTWARE QUALITY: A MEANS OF PROMOTING SOFTWARE PROCESS IMPROVEMENT , 1998 .

[9]  M. Prasanna,et al.  Validation of automated test cases with specification path , 2017 .

[10]  Sanmay Das,et al.  Filters, Wrappers and a Boosting-Based Hybrid for Feature Selection , 2001, ICML.

[11]  Salvatore Mamone,et al.  The IEEE standard for software maintenance , 1994, SOEN.

[12]  Arvinder Kaur,et al.  Statistical Comparison of Modelling Methods for Software Maintainability Prediction , 2013, Int. J. Softw. Eng. Knowl. Eng..

[13]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[14]  C. Chandrasekar,et al.  An Evolving Neuro-PSO-based Software Maintainability Prediction , 2018 .

[15]  David C. Yen,et al.  The characteristics of information system maintenance: an empirical analysis , 2014 .

[16]  Sallie M. Henry,et al.  Object-oriented metrics that predict maintainability , 1993, J. Syst. Softw..

[17]  Bo Yang,et al.  Software Maintainability Prediction Model Based on Fuzzy Neural Network , 2012, J. Multiple Valued Log. Soft Comput..

[18]  Chandrasekharan Rajendran,et al.  Determinants of software quality: Customer's perspective , 2003 .

[19]  Santanu Kumar Rath,et al.  Hybrid functional link artificial neural network approach for predicting maintainability of object-oriented software , 2016, J. Syst. Softw..