Cost-Effective Supervised Learning Models for Software Effort Estimation in Agile Environments

Abstract

Software development effort estimation is the process of predicting the most realistic effort required to develop or maintain software. It is important to develop estimation models and appropriate techniques to avoid losses caused by poor estimation. However, no method exists that is the most appropriate one for Agile Development where frequent iterations involve the customer causing time consuming estimation process. To address this an automated estimation methodology called "Auto-Estimate" is proposed complementing Agile's manual Planning Poker. The Auto-Estimate leverages features extracted from Agile story cards, and their actual effort time. The approach is justified by evaluating alternative machine learning algorithms for effort prediction. It is shown that selected machine learning methods perform better than Planning Poker estimates in the later stages of a project. This estimation approach is evaluated for accuracy, applicability and value, and the results are presented within a real-world setting.