APPLICATION OF ARTIFICIAL NEURAL NETWORKS IN PREDICTION OF SOFTWARE DEVELOPMENT EFFORT
Main Article Content
Abstract
Over the past two decades, there has been a great enhance in researches dealing with the software development effort estimation utilizing machine learning (ML) approaches with the objective of improving the accuracy of the estimates. Among these ML methods, artificial neural network approaches have gained significant scholarly attention thanks to their capability to learn and model non-linear and complex functions. In this paper, artificial neural network technique was considered for modelling software development effort estimation. Datasets considered for estimation were COCOMO. Evaluation measures used were MMRE and correlation R. After building and testing the ANN model, and based on the comparison between the test results of the ANN model and the SLIM, Function Points, and COCOMO-basic models it could be concluded that the ANN was a suitable model in the estimation of the effort. ANN is recommended to be used as a predictive model for software development effort estimation.
Downloads
Metrics
Article Details
Licensing
TURCOMAT publishes articles under the Creative Commons Attribution 4.0 International License (CC BY 4.0). This licensing allows for any use of the work, provided the original author(s) and source are credited, thereby facilitating the free exchange and use of research for the advancement of knowledge.
Detailed Licensing Terms
Attribution (BY): Users must give appropriate credit, provide a link to the license, and indicate if changes were made. Users may do so in any reasonable manner, but not in any way that suggests the licensor endorses them or their use.
No Additional Restrictions: Users may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.