On the value of filter feature selection techniques in homogeneous ensembles effort estimation

Hosni, Mohamed; Idri, Ali; Abran, Alain

doi:10.1002/smr.2343

Cited by 11 publications

(7 citation statements)

References 87 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hosni et al 32 Khan 33 used PSO, a bio-inspired feature selection technique. The author used three datasets: Albrecht, Desharnais, and COCOMO NASA, and RF, REPTree, SMOReg, LR, M5Rule, and MLP as estimation models.…”

Section: Related Workmentioning

confidence: 99%

Towards effective feature selection in estimating software effort using machine learning

Jadhav

Shandilya

2023

J Software Evolu Process

View full text Add to dashboard Cite

Software effort estimation is a vital process in the software industry for successfully administering 5Ds of the software development life cycle (SDLC). The 5Ds stand for demand, development, direction, deployment, and designated cost of the software. Software development effort estimation (SDEE) is an effort prediction mechanism to calculate the effort for the development of the software product in order to minimize the challenges in the software field. Academics and practitioners are striving to identify which machine learning estimation technique yields more accurate results based on evaluation metrics, datasets, and other pertinent aspects. The feature selection techniques impact accuracy by selecting the main and relevant features in the dataset and eliminating the redundant and irrelevant features in the dataset. To achieve accurate estimations, the paper utilizes feature selection algorithms, along with various machine learning techniques, which predict the desired effort and the performance of the model has been measured in terms of prediction accuracy, value, relative error, and mean absolute error. The datasets China and Maxwell are trained with the relevant features by applying feature selection algorithms, and estimation techniques are applied to predict the effort. The performance is compared with the regression models and feature selection techniques utilized by many authors previously. The result of the proposed methodology significantly gives the best performance with the combination of feature selection and estimation models than all regression models when applied alone, to both datasets. From the results, it is perceptible that random forest is performing well with the feature selection techniques and obtains the highest prediction accuracy of 99.33% with the China and 89.47% with the Maxwell datasets.

show abstract

Section: Related Workmentioning

confidence: 99%

Towards effective feature selection in estimating software effort using machine learning

Jadhav

Shandilya

2023

J Software Evolu Process

View full text Add to dashboard Cite

show abstract

“…They reported improved outcomes compared to single ABE models. Hosni et al 43 conducted an ensemble model based on four techniques comprising k‐nearest neighbor, multilayer perceptron, support vector regression, and decision trees. Also, they investigated filter feature selection techniques in the single and ensemble models.…”

Section: Literature Reviewmentioning

confidence: 99%

An evolutionary ensemble analogy‐based software effort estimation

Shahpar

Bardsiri

2021

Softw Pract Exp

View full text Add to dashboard Cite

Analogy-based estimation (ABE) is the most commonly applied method for estimating using software. Although there are several analogy-based estimation techniques, there is no consistent conclusion of which technique is the best in all circumstances. Therefore, this article presents an evolutionary ensemble ABE (EEABE) for software cost estimation. Ensemble effort estimation (EEE) models forecast software development endeavors through using multiple estimation methods. In this article, EEABE combines GA as an evolutionary algorithm with six ABE models. The proposed method has been evaluated on four well-known datasets comprising Maxwell, Albrecht, Kemerer, and Desharnais, by the k-fold cross-validation technique and based on the performance criteria of MRE, MMRE, MDMRE, BMMRE, and PRED(0.25).The simulation results demonstrate that the use of EEABE increases the accuracy of estimation and reduces the cost. Besides, EEABE is a flexible and adaptable model with any type of dataset and software development project, and it has been optimized with the possibility of using various ABE techniques.

show abstract

“…Finally, the relevant features are selected based on the cut-off of importance. Two approaches can be used to generate multiple models, namely homogenous ensemble approach and heterogeneous ensemble approach [24][25][26]. In a homogenous ensemble approach, multiple datasets are created from the same data by sub-setting the samples, features, or both followed by using a single technique to build the model on each of these datasets [25].…”

Section: Introductionmentioning

confidence: 99%

“…Two approaches can be used to generate multiple models, namely homogenous ensemble approach and heterogeneous ensemble approach [24][25][26]. In a homogenous ensemble approach, multiple datasets are created from the same data by sub-setting the samples, features, or both followed by using a single technique to build the model on each of these datasets [25]. In a heterogeneous ensemble approach, a single dataset is modeled using different techniques to generate multiple models [26].…”

Section: Introductionmentioning

confidence: 99%

Supervised Rank aggregation (SRA): A novel rank aggregation approach for ensemble-based feature selection

Jain

2022

Preprint

View full text Add to dashboard Cite

Background: Feature selection (FS) is critical for high dimensional data analysis. Ensemble based feature selection (EFS) is a commonly used approach to develop FS techniques. Rank aggregation (RA) is an essential step of EFS where results from multiple models are pooled to estimate feature importance. However, the literature primarily relies on rule-based methods to perform this step which may not always provide an optimal feature set. Method and Results: This study proposes a novel Supervised Rank Aggregation (SRA) approach to allow RA step to dynamically learn and adapt the model aggregation rules to obtain feature importance. The approach creates a performance matrix containing feature and model performance value from all models and prepares a supervised learning model to get the feature importance. Then, unsupervised learning is performed to select the features using their importance. We evaluate the performance of the algorithm using simulation studies and implement it into real research studies, and compare its performance with various existing RA methods. The proposed SRA method provides better or at par performance in terms of feature selection and predictive performance of the model compared to existing methods. Conclusion: SRA method provides an alternative to the existing approaches of RA for EFS. While the current study is limited to the continuous cross-sectional outcome, other endpoints such as longitudinal, categorical, and time-to-event medical data could also be used.

show abstract

On the value of filter feature selection techniques in homogeneous ensembles effort estimation

Cited by 11 publications

References 87 publications

Towards effective feature selection in estimating software effort using machine learning

Towards effective feature selection in estimating software effort using machine learning

An evolutionary ensemble analogy‐based software effort estimation

Supervised Rank aggregation (SRA): A novel rank aggregation approach for ensemble-based feature selection

Contact Info

Product

Resources

About