Features-Level Software Effort Estimation Using Machine Learning Algorithms

Software effort estimation is a paramount mission in the software development process, which covered by project managers and software engineers. In the early stages, software system features are the only available measures. Therefore, cost estimation is a mission that comes under the planning stage of software venture management. In this paper, various machine learning algorithms are used to build software effort estimation models from software features. Artificial Neural Network (ANN), Support Vector Machines (SVM), K-star, and Linear Regression machine learning algorithms are evaluated on a public dataset with actual software efforts. Results showed that machine learning approach can be dependable on predicting the future effort of a software system.