ENNA: software effort estimation using ensemble of neural networks with associative memory

Authors:
Yigit Kultur;Burak Turhan;Ayse Basar Bener
Affiliations:
Bogazici University, Bebek, Istanbul, Turkey;Bogazici University, Bebek, Istanbul, Turkey;Bogazici University, Bebek, Istanbul, Turkey
Venue:
Proceedings of the 16th ACM SIGSOFT International Symposium on Foundations of software engineering
Year:
2008

Citing 19
Cited 5

An empirical validation of software cost estimation models

Communications of the ACM
The role of programming language in estimating software development costs

Journal of Management Information Systems
Effort estimation in a system development project

Journal of Systems Management
Software engineering metrics and models

Software engineering metrics and models
The ART of Adaptive Pattern Recognition by a Self-Organizing Neural Network

Computer
Self-organization and associative memory: 3rd edition

Self-organization and associative memory: 3rd edition
Multilayer feedforward networks are universal approximators

Neural Networks
Neural networks and the bias/variance dilemma

Neural Computation
Machine Learning Approaches to Estimating Software Development Effort

IEEE Transactions on Software Engineering
Estimating Software Project Effort Using Analogies

IEEE Transactions on Software Engineering
Lessons learned from 25 years of process improvement: the rise and fall of the NASA software engineering laboratory

Proceedings of the 24th International Conference on Software Engineering
Improving Size Estimates Using Historical Data

IEEE Software
Guest Editors' Introduction: Global Software Development

IEEE Software
AI Tools for Software Development Effort Estimation

SEEP '96 Proceedings of the 1996 International Conference on Software Engineering: Education and Practice (SE:EP '96)
The software maintenance project effort estimation model based on function points

Journal of Software Maintenance: Research and Practice
COCOMO-Based Effort Estimation for Iterative and Incremental Software Development

Software Quality Control
Introduction to Machine Learning (Adaptive Computation and Machine Learning)

Introduction to Machine Learning (Adaptive Computation and Machine Learning)
A Systematic Review of Software Development Cost Estimation Studies

IEEE Transactions on Software Engineering
A study of cross-validation and bootstrap for accuracy estimation and model selection

IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 2

Learning to change projects

Proceedings of the 8th International Conference on Predictive Models in Software Engineering
Software effort models should be assessed via leave-one-out validation

Journal of Systems and Software
On the value of outlier elimination on software effort estimation research

Empirical Software Engineering
AREION: Software effort estimation based on multiple regressions with adaptive recursive data partitioning

Information and Software Technology
Potential and limitations of the ISBSG dataset in enhancing software engineering research: A mapping review

Information and Software Technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

Companies usually have limited amount of data for effort estimation. Machine learning methods have been preferred over parametric models due to their flexibility to calibrate the model for the available data. On the other hand, as machine learning methods become more complex they need more data to learn from. Therefore the challenge is to increase the performance of the algorithm when there is limited data. In this research we used a relatively complex machine learning algorithm, neural networks, and showed that stable and accurate estimations are achievable with an ensemble using associative memory. Our experimental results revealed that our proposed algorithm (ENNA) achieves on the average PRED(25) = 36.4 which is a significant increase compared to Neural Network (NN) PRED(25) = 8.