Software Development Effort Estimation Using Ensemble Machine Learning

doi:10.15242/ijccie.e0317026

Cited by 7 publications

(4 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is hard to quickly and accurately predict the development budget at the planning stage because the documentation is generally incomplete. For this reason, various procedures have been created to accurately predict construction costs with the limited project data available in the early phase [3]. Three known models are used to estimate the project effort, cost, and resources: Constructive Cost Model (COCOMO), Analogy-based Model, and Use Case Points model.…”

Section: Article Historymentioning

confidence: 99%

“…Therefore, using optimization algorithm approaches is highly advantageous to use a more structured estimation process [26]- [28]. This paper aims to objectively estimate software effort by using optimization algorithm approaches despite using subjective and time-consuming estimation methods like expert judgment and estimation by analogy [3] [29].…”

Section: Software Effort Estimationmentioning

confidence: 99%

“…An accurate effort estimation leads to the effective and efficient development of software and decreased risks [1] [2]. Estimations aim to accurately and control the cost and time boundaries of the project planning [3] [4]. The key parameters of effort estimation are time and cost, which are based on two reasons: to present software that is adaptable in a limited time frame and fill the gap between software and hardware progressions; and to generate software under the budget and time as responding to changeable customer demands [5] [6].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Optimized COCOMO parameters using hybrid particle swarm optimization

Zakaria

Ismail

Abidin

et al. 2021

Int. J. Adv. Intell. Informatics

View full text Add to dashboard Cite

Software effort and cost estimation are crucial parts of software project development. It determines the budget, time, and resources needed to develop a software project. The success of a software project development depends mainly on the accuracy of software effort and cost estimation. A poor estimation will impact the result, which worsens the project management. Various software effort estimation model has been introduced to resolve this problem. COnstructive COst MOdel (COCOMO) is a well-established software project estimation model; however, it lacks accuracy in effort and cost estimation, especially for current projects. Inaccuracy and complexity in the estimated effort have made it difficult to efficiently and effectively develop software, affecting the schedule, cost, and uncertain estimation directly. In this paper, Particle Swarm Optimization (PSO) is proposed as a metaheuristics optimization method to hybrid with three traditional state-of-art techniques such as Support Vector Machine (SVM), Linear Regression (LR), and Random Forest (RF) for optimizing the parameters of COCOMO models. The proposed approach is applied to the NASA software project dataset downloaded from the promise repository. Comparing the proposed approach has been made with the three traditional algorithms; however, the obtained results confirm low accuracy before hybrid with PSO. Overall, the results showed that PSOSVM on the NASA software project dataset could improve effort estimation accuracy and outperform other models.

show abstract

Section: Article Historymentioning

confidence: 99%

Section: Software Effort Estimationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Optimized COCOMO parameters using hybrid particle swarm optimization

Zakaria

Ismail

Abidin

et al. 2021

Int. J. Adv. Intell. Informatics

View full text Add to dashboard Cite

show abstract

“…[2] LITERATURE REVIEW [5] The purpose of this project was to replace subjective and time-consuming estimating methods with machine learning algorithms that could evaluate software effort objectively. On the Desharnais and Maxwell public datasets, models using the two machine learning techniques Support Vector Machine (SVM) and K-Nearest Neighbour (k-NN) separately and combining those together using ensemble learning, were tested.…”

Section: [1] Introductionmentioning

confidence: 99%

Ensemble Machine Learning and Software Development Effort Estimation

Gora,

Sinha

2023

JAC

View full text Add to dashboard Cite

Effort estimation is a crucial component of software development that aids in re-source allocation and planning for project managers. While faulty estimation can lead to cost overruns and project failure, an accurate estimation can stop project delays and overruns. Increasingly used in recent years for software development effort estimation, ensemble approaches combine numerous models to increase pre-diction accuracy and stability. This study investigates various ensemble learning approaches and assesses how well they work on a dataset of actual software projects. The findings demonstrate that ensembles perform better than single models and can estimate effort with high accuracy. This work also offers insights into the parameters, such as the diversity of models and the quality of input information, that influence the performance of ensemble approaches. The results indicate that ensemble approaches, which can be implemented using a variety of techniques like bagging, boosting, and stacking, can be a feasible strategy for enhancing software development effort estimation. However, the success of these methods depends on the careful selection of models and characteristics.

show abstract