Software Effort Estimation using Machine Learning Techniques with Robust Confidence Intervals

Braga, Petrônio L.; Oliveira, Adriano L. I.; Meira, Sílvio R. L.

doi:10.1109/ichis.2007.4344078

Cited by 22 publications

(22 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In particular, they exploited a Genetic Algorithm (GA) previously used to solve classification problems (Huang and Wang 2006) to address the problems of feature selection and SVR parameters optimization aiming to obtain better software effort estimations. The Desharnais and NASA datasets were also employed in this study and the results showed that the proposed GA-based approach was able to improve the performance of SVR and outperformed the previous results (Braga et al 2007;Oliveira 2006). As in our case study, they exploited a leave-one-out cross validation on the training set to obtain the parameter settings.…”

Section: Related Workmentioning

confidence: 97%

“…By using a leave-oneout cross-validation, the author reported that SVR significantly outperformed both linear regression and Radial Basis Function Networks (RBFNs), in terms of the indicators MMRE and Pred (25). In a second study (Braga et al 2007), the authors proposed a method based on machine learning that provided an effort estimate and corresponding confidence interval.…”

Section: Related Workmentioning

confidence: 99%

“…As evaluation criteria the above approaches used MMRE and Pred (25), while we employed more summary measures (i.e., MdMRE, MEMRE, and MdEMRE), boxplots of absolute residuals, and tests to verify the statistical significance of the results. Moreover, differently from the proposals described above (Braga et al 2007, 2008, Huang and Wang 2006, Oliveira 2006 we investigated different configurations of SVR by considering two different dependent variables, i.e., EFH and 1/EFH, and two preprocessing strategies, i.e., Normalization and Log Transformation. Furthermore, we analyzed the use of three kernels, i.e., Linear, Polynomial, and RBF while they used only Linear and RBF kernels.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Investigating the use of Support Vector Regression for web effort estimation

et al. 2010

View full text Add to dashboard Cite

Support Vector Regression (SVR) is a new generation of Machine Learning algorithms, suitable for predictive data modeling problems. The objective of this paper is twofold: first, to investigate the effectiveness of SVR for Web effort estimation using a cross-company dataset; second, to compare different SVR configurations looking at the one that presents the best performance. In particular, we took into account three variables' preprocessing strategies (no-preprocessing, normalization, and logarithmic), in combination with two different dependent variables (effort and inverse effort). As a result, SVR was applied using six different data configurations. Moreover, to understand the suitability of kernel functions to handle non-linear problems, SVR was applied without a kernel, and in combination with the Radial Basis Function (RBF) and the Polynomial kernels, thus obtaining 18 different SVR configurations. To identify, for each configuration, which were the best values for each of the parameters we defined a procedure based on a leave-one-out cross-validation approach. The dataset employed was the Tukutuku database, which has been adopted in many previous Web effort estimation studies. Three different training and test set splits were used, including respectively 130 and 65 projects. The SVR-based predictions were also benchmarked against predictions obtained using Manual StepWise Empir Software Eng (2011) 16:211-243 Regression and Case-Based Reasoning. Our results showed that the configuration corresponding to the logarithmic features' preprocessing, in combination with the RBF kernel provided the best results for all three data splits. In addition, SVR provided significantly superior prediction accuracy than all the considered benchmarking techniques.

show abstract

Section: Related Workmentioning

confidence: 97%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Investigating the use of Support Vector Regression for web effort estimation

et al. 2010

View full text Add to dashboard Cite

show abstract

“…By using a leave-one-out cross-validation, the author reported that SVR significantly outperformed both linear regression and Radial Basis Function Networks (RBFNs), in terms of the indicators MMRE and Pred (25). In the second study, the authors proposed a method based on machine learning that provided an In particular, they employed robust confidence intervals, which are not associated with the probability distributions of the errors in the training set [4]. To assess the defined method, they performed a case study using the Desharnais [10] and NASA [2] datasets.…”

Section: Related Workmentioning

confidence: 99%

“…The first study that applied SVR for software effort estimation [31] used data on 18 software projects from a NASA dataset [2] and reported that SVR significantly outperformed both linear regression and Radial Basis Function Networks (RBFNs). The second study [4] compared various AI-based effort prediction techniques using two single-company datasets. Their results corroborated those from [31], showing that SVR performed very well.…”

Section: Introductionmentioning

confidence: 99%

Applying support vector regression for web effort estimation using a cross-company dataset

Corazza

Martino

Ferrucci

et al. 2009

2009 3rd International Symposium on Empirical Software Engineering and Measurement

View full text Add to dashboard Cite

Support Vector Regression (SVR) is a new generation of Machine Learning algorithms, suitable for predictive data modeling problems. The objective of this paper is to investigate the effectiveness of SVR for Web effort estimation, in particular when dealing with a cross-company dataset. To gain a deeper insight on the method, we carried out an empirical study using four kernels for SVR, namely linear, polynomial, Gaussian, and sigmoid. Moreover, we used two variables’ preprocessing strategies (normalization and logarithmic), and two different dependent variables (effort and inverse effort). As a result, SVR was applied using six different configurations for each kernel. As for the dataset, we employed the Tukutuku database, which is widely adopted in Web effort estimation studies. A hold-out approach was adopted to evaluate the prediction accuracy for all the configurations, using two training sets, each containing data on 130 projects randomly selected, and two test sets, each containing the remaining 65 projects. As benchmark, SVR-based predictions were also compared to predictions obtained using Manual StepWise Regression, Case-Based Reasoning, and Bayesian Networks. Our results suggest that SVR performed well, since on the first hold-out, the linear kernel with a logarithmic transformation of variables provided significantly superior prediction accuracy than all the other techniques, while for the second hold-out, the Gaussian kernel achieved significantly superior predictions than all other techniques, except for Manual StepWise Regression

show abstract

Empirical evaluation of an entropy‐based approach to estimation variation of software development effort

Koutbi

Idri

Abran

2018

J Software Evolu Process

View full text Add to dashboard Cite

As effort estimation has gained increasing attention, most of the techniques proposed have focused on the accuracy of effort estimates. Yet no clear conclusions have been drawn on which techniques perform best in all contexts. We propose an entropy‐based approach to effort estimate variation caused by measurement and model error sources whatever the effort estimation technique used. The proposed approach was empirically evaluated by exploring three entropy formulae, four interpolation methods, and two analogy‐based effort estimation approaches (crisp and fuzzy analogy) over seven datasets using the Jackknife evaluation method. The obtained results show that the three entropy formulae have in general the same positive influence on the performance of the entropy‐based approach measured in terms of absolute error of effort deviation. In addition, the spline interpolation outperformed all other interpolation methods, using any of the entropy formulae. Moreover, achievement percentages of the best variants of our approach closely approximated those of the Gaussian distribution confirming that the Gaussian distribution is useful for characterizing effort estimate variation.

show abstract

Software Effort Estimation using Machine Learning Techniques with Robust Confidence Intervals

Cited by 22 publications

References 0 publications

Investigating the use of Support Vector Regression for web effort estimation

Investigating the use of Support Vector Regression for web effort estimation

Applying support vector regression for web effort estimation using a cross-company dataset

Empirical evaluation of an entropy‐based approach to estimation variation of software development effort

Contact Info

Product

Resources

About