Artificial Neural Network Architectures and Orthogonal Arrays in Estimation of Software Projects Efforts Estimation : PLENARY TALK

Abstract

In the software engineering, estimation of the effort, time and cost required for the development of software projects is an important issue. It is a very difficult task for project managers to predict the cost and effort needed in the premature stages of planning. Software estimation ahead of development can reduce the risk and increase the success rate of the project. Many traditional and machine learning methods are used for software effort estimation by researchers, but always it has been a challenge to predict the effort accurately. In our study, different Artificial Neural Network (ANN) used for effort estimation is discussed. It is observed that the prediction of software effort by using ANN is more precise and better compared to traditional methods such as Function point, Use-case methods and COCOMO etc. Models based on neural networks are competitive in nature as compared to statistical and traditional regression methods. This talk explains the overview of various ANN architectures, and deep learning networks used by the researchers for software effort estimation (SEE). In addition, we have set out own criteria, which has been used to compare all the different selected methods. We have also given a score for each evaluation criteria, so that we can compare the different methods numerically for cost estimation. Our observations have shown that it is best to use a number of different estimating techniques or cost models, and then compare the results before determining the reasons for any of the large variations. None of the methods are necessarily better or worse than the others. We found, in fact, that their strengths and weaknesses often complement each other. Therefore, the main conclusion is that there is no one single technique that is best for every situation, and the results of a number of different approaches need to be carefully considered to discover what is the most likely to produce estimates that are realistic.