Heterogeneous Ensemble Model to Optimize Software Effort Estimation Accuracy

Syed Sarmad Ali

doi:10.1109/ACCESS.2023.3256533

Heterogeneous Ensemble Model to Optimize Software Effort Estimation Accuracy

2023-01-01

15

OA

AI

DOI：10.1109/ACCESS.2023.3256533

原文链接

原文求助

摘要

En 中文

The software industry has experienced rapid expansion in recent years, with software development now essential to the success of many multinational corporations. The demand for complex software systems has dramatically increased, effective software development has become crucial, given the limitations of resources such as money, time, and labor. Cost and effort calculations significantly impact the development process and client needs, and project failure is often caused by errors in job estimating. Underestimating a project's cost and effort can have severe repercussions, such as exceeding the project's budget. Project overruns, on the other hand, can also have a detrimental impact on software projects' successful completion. Researchers and experts in the software industry are continually exploring ways to keep management and development productivity at high levels. However, standalone estimating models have revealed inadequacies over the last decade, and they have not produced any noteworthy research results. Recent literature suggests that opting for ensemble models would yield better results than standalone models. We have proposed a heterogeneous ensemble effort estimation (EEE) model in this research. Our proposed model comprises standalone estimating models such as Use Case Point, Expert Judgment (EJ), and Artificial Neural Network (ANN). We combined the effort of each unique base model using linear combination rule. To validate our model's effectiveness, we applied it to the benchmark dataset, the International Software Benchmarking Standards Group (ISBSG), using three different variations to avoid biases. We further applied the trained models to industry use cases for cross-validation. Our study's findings demonstrated that, in comparison to stand-alone estimate strategies, the ensemble technique produced better estimation results. Finally, our study proposes a heterogeneous ensemble effort estimation model that outperforms standalone models in terms of accuracy. This model has the potential to aid in effective software development, particularly in project cost and effort estimation.

Keyword:

Software

Estimation

Costs

Artificial neural networks

Software algorithms

Predictive models

Machine learning algorithms

Software effort estimation

ensemble effort estimation (EEE)

standalone estimation

use case point (UCP)

machine learning algorithms

deep learning

expert judgement

Heterogeneous Ensemble Model to Optimize Software Effort Estimation Accuracy

摘要

期刊

机构

引用论文