An adaptive learning approach to software cost estimation

Kaushik, Anupama; Soni, Ajay; Soni, Rachna

doi:10.1109/ncccs.2012.6413029

Cited by 19 publications

(8 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the testing mode, the trained network is evaluated by the test data which comprise of data from NASA projects. Evaluation criteria of software effort estimation include [4,5,6]:…”

Section: Methodsmentioning

confidence: 99%

Automation of Software Cost Estimation using Neural Network Technique

Kumar¹,

Bhatia²

2014

IJCA

View full text Add to dashboard Cite

Software cost estimation is one of the most challenging tasks in software engineering. Over the past years the estimators have used parametric cost estimation models to establish software cost, however the challenges to accurate cost estimation keep evolving with the advancing technology. A detailed review of various cost estimation methods developed so far is presented in this paper. Planned effort and actual effort has been comparison in detail through applying on NASA projects. This paper uses Back-Propagation neural networks for software cost estimation. A model based on Neural Network has been proposed that takes KLOC of the project as input, uses COCOMO model parameters and gives effort as output. Artificial Neural Network represents a complex set of relationship between the effort and the cost drivers and is a potential tool for estimation. The proposed model automates the software cost estimation task and helps project manager to provide fast and realistic estimate for the project effort and development time that in turn gives software cost. General TermsSoftware Engineering, Software Planning.

show abstract

“…In the testing mode, the trained network is evaluated by the test data which comprise of data from NASA projects. Evaluation criteria of software effort estimation include [4,5,6]:…”

Section: Methodsmentioning

confidence: 99%

Automation of Software Cost Estimation using Neural Network Technique

Kumar¹,

Bhatia²

2014

IJCA

View full text Add to dashboard Cite

show abstract

“…MVR and multivariate linear regression (MLR) analysis are compared and it is found that MVR is more accurate than the MLR. A tool is proposed to estimate the cost and risk of software projects [27]. The objective of this research is to combine function point and risk management process.…”

Section: Related Workmentioning

confidence: 99%

Proposed Risk Management Model to Handle Changing Requirements

Aljohani¹,

Qureshi²

2019

IJEME

View full text Add to dashboard Cite

The change in requirements while construction of a software may bring into several risks like over budget and extra schedule. The changes in requirements are considered as a high risk to fail the software projects. A good project manager always incorporates risk management paradigm to manage the risks of changing requirements. This research uses available statistical techniques to estimate the cost of risk management with respect to the changing requirement. In addition, a hybrid cost estimation model is proposed using action strategy model to counteract, mitigate and manage the risks of changing requirements. The proposed model is validated using an industrial case study in Saudi Electricity Company (SEC) to conclude the results. The results are found supportive because the proposed model shows significant improvement to estimate the costs of changing requirements as compared to the existing cost estimation models.

show abstract

“…Neural network approximation and analogy are some of the examples for this categorization [23]. The previous method is based on learning phase, training and the future one is based on the estimation of an expert and comparison with the outcome obtained from the past data of the same software project [21].…”

Section: Learning Basedmentioning

confidence: 99%