Improvement of effort estimation accuracy in software projects using a feature selection approach

In recent years, utilization of feature selection techniques has become an essential requirement for processing and model construction in different scientific areas. In the field of software project effort estimation, the need to apply dimensionality reduction and feature selection methods has become an inevitable demand. The high volumes of data, costs, and time necessary for gathering data , and also the complexity of the models used for effort estimation are all reasons to use the methods mentioned. Therefore, in this article, a genetic algorithm has been used for feature selection in the field of software project effort estimation. This technique has been tested on well-known data sets. Implementation results indicate that the resulting subset, compared to the original data set, has produced better outcomes in terms of effort estimation accuracy. This article showed that genetic algorithms are ideal methods for selecting a subset of features and improving effort estimation accuracy.