Efficient Resource Allocation Using Gradient Boosting Algorithm for Agile-Scrum Methodologies

Abstract

This paper proposes a novel approach to dynamic resource allocation in distributed agile development using the Scrum-tree-k-nearest neighbor's algorithm with Gradient boosting. The aim is to improve the efficiency and effectiveness of the development process by dynamically allocating resources based on project features. The proposed algorithm is evaluated using the Agile Project Data dataset, which contains data from 15 distributed agile development projects. Average effort estimation is used as the performance metric to evaluate the algorithm's performance. The results show that the proposed algorithm outperforms traditional resource allocation methods and achieves a higher accuracy rate in predicting the required resources for each sprint. The proposed algorithm has the potential to enhance the outcomes of future agile development projects by mitigating the risks associated with traditional software development life cycle.