An Optimized Analogy-Based Project Effort Estimation

TL;DR

This paper introduces an optimized analogy-based effort estimation model that improves prediction accuracy by better selecting the number of analogies and adjustment techniques, adapting to project-specific features.

Contribution

It proposes a new adjusted ABE model that optimizes the relationship between features and effort estimates, enhancing predictive performance.

Findings

Improved accuracy of effort estimates with the new model

Variable optimal number of analogies per project

Enhanced adjustment techniques for better predictions

Abstract

Despite the predictive performance of Analogy-Based Estimation (ABE) in generating better effort estimates, there is no consensus on how to predict the best number of analogies, and which adjustment technique produces better estimates. This paper proposes a new adjusted ABE model based on optimizing and approximating complex relationships between features and reflects that approximation on the final estimate. The results show that the predictive performance of ABE has noticeably been improved, and the number of analogies was remarkably variable for each test project.