AdamOptimizer for the optimisation of Use Case Points estimation

Abstract

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. © 2020, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG.