Software Effort Prediction Using Ensemble Learning Methods

Alhazmi, Omar H.; Khan, Mohammed Zubair

doi:10.4236/jsea.2020.137010

Cited by 12 publications

(5 citation statements)

References 26 publications

(21 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With an MMRE value of 10% and a PRED(0.25) of 97%, the M5 rule ensemble was found to be the best way to estimate effort. 66 The above are some experimental studies on ensemble methods that are performed from time to time. Table 1 summarizes other related work on software effort estimation of various single methods using known datasets and real-time industrial projects, and the performance metrics were evaluated to determine the best model for estimating effort accuracy.…”

Section: Ensemble Effort Estimation Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Incorporating statistical and machine learning techniques into the optimization of correction factors for software development effort estimation

Nhung,

Van Hai,

Silhavy

et al. 2023

J Software Evolu Process

View full text Add to dashboard Cite

Accurate effort estimation is necessary for efficient management of software development projects, as it relates to human resource management. Ensemble methods, which employ multiple statistical and machine learning techniques, are more robust, reliable, and accurate effort estimation techniques. This study develops a stacking ensemble model based on optimization correction factors by integrating seven statistical and machine learning techniques (K‐nearest neighbor, random forest, support vector regression, multilayer perception, gradient boosting, linear regression, and decision tree). The grid search optimization method is used to obtain valid search ranges and optimal configuration values, allowing more accurate estimation. We conducted experiments to compare the proposed method with related methods, such as use case points‐based single methods, optimization correction factors‐based single methods, and ensemble methods. The estimation accuracies of the methods were evaluated using statistical tests and unbiased performance measures on a total of four datasets, thus demonstrating the effectiveness of the proposed method more clearly. The proposed method successfully maintained its estimation accuracy across the four experimental datasets and gave the best results in terms of the sum of squares errors, mean absolute error, root mean square error, mean balance relative error, mean inverted balance relative error, median of magnitude of relative error, and percentage of prediction (0.25). The p‐value for the t‐test showed that the proposed method is statistically superior to other methods in terms of estimation accuracy. The results show that the proposed method is a comprehensive approach for improving estimation accuracy and minimizing project risks in the early stages of software development.

show abstract

Section: Ensemble Effort Estimation Methodsmentioning

confidence: 99%

“…The authors conducted a comparative study of 12 ensemble methods for effort estimation. With an MMRE value of 10% and a PRED(0.25) of 97%, the M5 rule ensemble was found to be the best way to estimate effort 66 …”

Section: Related Workmentioning

confidence: 99%

Incorporating statistical and machine learning techniques into the optimization of correction factors for software development effort estimation

Nhung,

Van Hai,

Silhavy

et al. 2023

J Software Evolu Process

View full text Add to dashboard Cite

show abstract

“…The results of this experiment showed that the effort accuracy equals 85% when applying a solo method and 91.35% using the combined classifiers. Alhazmi 41 examined the effect of two feature selection algorithms Best Fit and GA on six ensemble learning algorithms. The GA feature selection for the bagging M5Rule was the best method for predicting software effort.…”

Section: Related Workmentioning

confidence: 99%

“…and Khan, M.Z. [41] examined the effect of two feature selection algorithms Best Fit and Genetic Algorithm on six ensemble learning algorithms. The Genetic Algorithm (GA) feature selection for the bagging M5Rule was the best method for predicting software development effort.…”

Section: Figure 1 Categorization Of Effort Estimation Modelsmentioning

confidence: 99%

Software effort estimation accuracy prediction of machine learning techniques: A systematic performance evaluation

et al. 2021

View full text Add to dashboard Cite

Software effort estimation accuracy is a key factor in effective planning, controlling, and delivering a successful software project within budget and schedule.The overestimation and underestimation both are the key challenges for future software development, henceforth there is a continuous need for accuracy in software effort estimation. The researchers and practitioners are striving to identify which machine learning estimation technique gives more accurate results based on evaluation measures, datasets and other relevant attributes. The authors of related research are generally not aware of previously published results of machine learning effort estimation techniques. The main aim of this study is to assist the researchers to know which machine learning technique yields the promising effort estimation accuracy prediction in software development. In this article, the performance of the machine learning ensemble and solo techniques are investigated on publicly and non-publicly domain datasets based on the two most commonly used accuracy evaluation metrics. We used the systematic literature review methodology proposed by Kitchenham and Charters. This includes searching for the most relevant papers, applying quality assessment (QA) criteria, extracting data, and drawing results. We have evaluated a state-of-the-art accuracy performance of 35 selected studies (17 ensemble, 18 solo) using mean magnitude of relative error and PRED (25) as a set of reliable accuracy metrics for performance evaluation of accuracy among two techniques to report the research questions stated in this study. We found that machine learning techniques are the most frequently implemented in the construction of ensemble effort estimation (EEE) techniques. The results of this study revealed that the EEE techniques usually yield a promising estimation accuracy than the solo techniques.

show abstract

“…MMRE, PRED-prediction at 0.25, 0.50, and 0.75 power levels, Root Relative Squared Error, and Relative Absolute Error are used as evaluation measures. In this paper, a feature selection technique[18] based on CfsSubsetEval with BestFit and a genetic algorithm is applied. Based on the results, the best way to estimate software work is through genetic algorithm feature selection for M5Rule.Halcyon and colleagues offered eight different ensemble approaches for estimating effort.…”

mentioning

confidence: 99%

Software Effort Estimation using Base Ensembled Regression Techniques and Principal Components Regression as Super Learner

G¹,

2023

Preprint

View full text Add to dashboard Cite

With the increased expectation of faster and more modern software products for the digital market, providing accurate, qualitative, costeffective and time-bound software is crucial. Effective Software Project planning and Estimations are vital steps for developing a software product. The most precise effort in person-months or person-hours is predicted by software effort estimate. Inaccurate Estimations of effort provided by several estimation techniques have led to complications in the implementation of project, budget and schedule. Regression methods were the most common statistical method used for predicting modelling. Ensemble approaches use multiple learning algorithms to provide a better predictive model than individual learners. Our proposed scheme is stacked ensemble technique that used Decision Tree, Principal Components Regression (PCR), Random Forest, NeurelNet, glmnet, XGBoost, Earth and Support Vector Machine as base ensembled regression techniques. PCR as a Super learner was shown to be the best technique for assessing effort after extensive testing with a variety of super learners. Estimators were evaluated using the Mean Absolute Error (MAE), the Root Mean Squared Error (RMSE), the Mean Squared Error (MSE), the percentage of close approximations within 25 Percent of the true values (PRED (25)), and the R-squared coefficients.

show abstract

Software Effort Prediction Using Ensemble Learning Methods

Cited by 12 publications

References 26 publications

Incorporating statistical and machine learning techniques into the optimization of correction factors for software development effort estimation

Incorporating statistical and machine learning techniques into the optimization of correction factors for software development effort estimation

Software effort estimation accuracy prediction of machine learning techniques: A systematic performance evaluation

Software Effort Estimation using Base Ensembled Regression Techniques and Principal Components Regression as Super Learner

Contact Info

Product

Resources

About