Integrating uncertainty in software effort estimation using Bootstrap based Neural Networks

摘要

Software effort estimation is a crucial task in the software project management. It is the basis for subsequent planning, control, and decision-making. Reliable effort estimation is difficult to achieve, especially because of the inherent uncertainty arising from the noise in the dataset used for model elaboration and from the model limitations. This research paper proposes a software effort estimation method that provides realistic effort estimates by taking into account uncertainty in the effort estimation process. To this end, an approach to introducing uncertainty in Neural Network based effort estimation model is presented. For this purpose, bootstrap resampling technique is deployed. The proposed method generates a probability distribution of effort estimates from which the Prediction Interval associated to a confidence level can be computed. This is considered to be a reasonable representation of reality, thus helping project managers to make well-founded decisions. The proposed method has been applied on a dataset from International Software Benchmarking Standards Group and has shown better results compared to traditional effort estimation based on linear regression.