Regression Model for Software Effort Estimation Based on the Use Case Point Method

It is very important to conduct software estimation in the early stages of the software life cycle, because it helps managers bid on projects and allocate resources efficiently. This paper presents a novel regression model to estimate the software effort based on the use case point size metric. The use case point model takes use case diagrams as input and gives the software size in use case points as output. The proposed effort equation takes into consideration the non-linear relationship between software size and software effort, as well as the influences of project complexity and productivity. Results show that the software effort estimation accuracy can be improved by 16.5% using PRED(25) and 25% using PRED(35).