원문정보
초록
영어
Many comparative studies on the performance of machine learning (ML) techniques for web cost estimation (WCE) have been reported in the literature. However, not much attention have been given to understanding the conceptual differences and similarities that exist in the application of these ML techniques for WCE, which could provide credible guide for upcoming practitioners and researchers in predicting the cost of new web projects. This paper presents a comparative analysis of three prominent machine learning techniques – Case-Based Reasoning (CBR), Support Vector Regression (SVR) and Artificial Neural Network (ANN) – in terms of performance, applicability, and their conceptual differences and similarities for WCE by using data obtained from a public dataset (www.tukutuku.com). Results from experiments show that SVR and ANN provides more accurate predictions of effort, although SVR require fewer parameters to generate good predictions than ANN. CBR was not as accurate, but its good explanation attribute gives it a higher descriptive value. The study also outlined specific characteristics of the 3 ML techniques that could foster or inhibit their adoption for WCE.
목차
1. Introduction
2. Background and Related Work
2.1. Expert Judgment
2.2. Algorithmic Models
2.3. Machine Learning (ML) for Web Cost Estimation
2.4. Case-Based Reasoning (CBR)
2.5. Support Vector Regression (SVR)
2.6. Artificial Neural Network (ANN)
2.7. Related Work on Web Cost Estimation
3. Overview of Methodology
3.1. Procedure for CBR Experiment
3.2. Procedure for SVR Experiment
3.3. Procedure for ANN Experiment
4. Description of the Three ML Experiments
4.1. Conducting the Experiments
4.2. Conducting the SVR Experiment
4.3. Conducting the ANN Experiment
5. Comparative Analysis of the Machine Learning Techniques
5.1. Analysis of Performance of ML Techniques
5.2. Analysis of Conceptual Similarities of ML Techniques
5.3. Analysis of Conceptual Similarities of ML Techniques
6. Conclusion
References