Use Case Points is considered to be one of the most popular methods to estimate the size of a developed software project. Many approaches have been proposed to optimise Use Case Points. The Algorithmic Optimisation Method uses the Multiple Least Squares method to improve the accuracy of Use Case Points by finding optimal coefficient regressions, based on the historical data. This paper aims to propose a new approach to optimise the Use Case Points method based on Gradient Descent with the support of the TensorFlow package. The significance of its purpose is to conduct a new approach that might lead to more accurate prediction than that of the Use Case Points and the Algorithmic Optimisation Method. As a result, this new approach outweighs both the Use Case Points and the Algorithmic Optimisation Methods.
This paper presents a proposed method for improving the prediction ability of the Use Case Points method. Our main goal is to use the Least Absolute Shrinkage and Selection Operator Regression methods to find out which of the technical and environmental complexity factors significantly affect the accuracy of the Use Case Points method. Two regression models were used to calculate the selected significant variables. The results of several evaluation measures show that the proposed estimation method ability is better than the original Use Case Points method. The Sum of Squared Error of the proposed method is better than the results obtained by the original one. The study also enables project managers to understand how to assess the technical and environmental complexity factors better -since they do have an important impact on effort estimation.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.