Software Effort Estimation using Radial Basis and Generalized Regression Neural Networks

TL;DR

This paper develops neural network-based models for software effort estimation, using Radial Basis and Generalized Regression Neural Networks, and compares their performance with the COCOMO model on the COCOMO81 database.

Contribution

It introduces neural network models tailored for effort estimation that outperform traditional models like COCOMO in accuracy.

Findings

Radial Basis Neural Network outperforms other models in estimation accuracy.

Neural network models show improved performance over traditional COCOMO.

Evaluation using multiple criteria confirms the effectiveness of the proposed models.

Abstract

Software development effort estimation is one of the most major activities in software project management. A number of models have been proposed to construct a relationship between software size and effort; however we still have problems for effort estimation. This is because project data, available in the initial stages of project is often incomplete, inconsistent, uncertain and unclear. The need for accurate effort estimation in software industry is still a challenge. Artificial Neural Network models are more suitable in such situations. The present paper is concerned with developing software effort estimation models based on artificial neural networks. The models are designed to improve the performance of the network that suits to the COCOMO Model. Artificial Neural Network models are created using Radial Basis and Generalized Regression. A case study based on the COCOMO81 database compares the proposed neural network models with the Intermediate COCOMO. The results were analyzed using five different criterions MMRE, MARE, VARE, Mean BRE and Prediction. It is observed that the Radial Basis Neural Network provided better results