A Comprehensive Machine Learning Framework for Evaluating Agility of a Software Development Organization

Software project management has undergone significant development over the years due to the progress made in various techniques. Scrum is widely regarded as one of the most often employed methodologies, encompassing a range of stages from refinement to retrospective. It empowers individual teams to take ownership of their work and deliver on their commitments within a specified timeframe. This presents numerous issues for upper level management regarding product delivery and engineering. This study examines a novel method of estimating work based on complexity instead of estimating effort based on hours. It presents a new approach to combining this framework and using it to measure and predict organizational efficiency using K-nearest neighbor and decision tree algorithms. This article will examine scenarios that elucidate how velocity-driven planning can assist a software organization in effectively delivering business value to its customers. It will utilize a synthetic dataset to demonstrate how current datasets can assist a scrum master or project lead in forecasting and organizing future sprints and dividing backlogs into manageable tasks using tools, such as Jira. This results in higher accuracy, as seen for organization 2 with 87% and 95% for organization 3, respectively, via experiments, and showcases the maturity growth over time.