Reducing the Uncertainty of Agile Software Development Using a Random Forest Classification Algorithm

Background: Companies operating in the software industry or those which rely on new technologies are facing a rising level of complexity in building products. To address these new circumstances, enterprises are investing more resources in modern approaches to software delivery, such as agile methodologies. Amongst these methodologies, relative effort estimation is widely adopted. Outcomes of the estimation process are often not predictable or reliable. Aims: The objective of this paper is to research the random forest classification algorithm’s effectiveness for high-level effort estimating. Method: Authors are focusing on defining complexity factors that are treated as model features. In addition, the authors have empirically tested the proposed solution in a commercial environment. Besides these, authors have analyzed the effective impact of each complexity factor. The analysis was done on the set of seventy thousands of Jira work items. Observation has been made empirically across four major releases. Results: The results indicate that the empirical way of defining model features has a significant impact on effort estimation accuracy. During research, the authors have found several key factors that have a significant impact on model accuracy. Teams that are using agile techniques or methods for effort estimation can enhance planning outcomes with tools supporting high-level estimation. Finding out and fine-tuning such tools needs a structured process for finding the most significant key complexity factors. Conclusion: Usage of metrics such as effort estimations and their accuracy in the software development process in agile organizations could lead to more accurate planning and forecasting of project outcomes. Problems with planning on program level could also be actioned with a structured estimation framework, enhanced by modern tools such as classification models. We should remember that complexity is growing with scaling delivery structures within companies.