Abstract
There is no doubt that the software industry is one of the fastest-growing sectors on the planet today. As the cost of the entire development process continues to rise, an effective mechanism is needed to estimate the required development cost to control better the cost overrun problem and make the final software product more competitive. However, in the early stages of planning, the project managers have difficulty estimating the realistic value of the effort and cost required to execute development activities. Software evaluation prior to development can minimize risk and upsurge project success rates. Many techniques have been suggested and employed for cost estimation. However, computations based on several of these techniques show that the estimation of development effort and cost vary, which may cause problems for software industries in allocating overall resources costs. The proposed research study proposes the artificial neural network (ANN) based Neural-Evolution technique to provide more realistic software estimates in the early stages of development. The proposed model uses the advantages of the topology augmentation using an evolutionary algorithm to automate and achieve optimality in ANN construction and training. Based on the results and performance analysis, it is observed that software effort prediction using the proposed approach is more accurate and better than other existing approaches.
Highlights
The software industry is undoubtedly one of the greatest innovations in the modern world [1]
This paper suggests a unique approach to software development cost estimation based on Neuro-evolution
Cost estimation is the key concern in the software industry
Summary
The software industry is undoubtedly one of the greatest innovations in the modern world [1]. An overestimated cost can lead to higher software costs, a waste of resources, and even loss of opportunities for competing markets [3] These factors can have negative consequences for the project, the development organization, and the customers. The existing approaches for the estimation, such as COCOMO and iii) function point-based model, all lack providing desirable accuracy as they ignore many of the critical drivers. These methods limit their applicability in the real-time scenario. In order to address these challenges, the soft-computing approaches are being extensively attracted the focus of the researchers by including approaches either individual or by hybrid techniques like- swarm optimization, fuzzy logic, genetic algorithm, machine learning, and neural network [810].
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
