The adjusted analogy-based software effort estimation based on similarity distances

Chiu, Nan-Hsing; Huang, Sun-Jen

doi:10.1016/j.jss.2006.06.006

Cited by 161 publications

(127 citation statements)

References 27 publications

Supporting

Mentioning

116

Contrasting

Unclassified

Order By: Relevance

“…This is different from the proposal studied by Chiu and Huang [9] which relied on MMRE and PRED. Earlier in this section, we discussed why these two measures are no longer believed to be the trustworthy measures.…”

Section: Gacontrasting

confidence: 68%

“…In this calculation, the software size variable may be measured in terms such as adjusted Function Points, raw Function Points, or lines of code. Walkerden and Jeffery [5], based on their [5] Linear size adaptation Linear Software size 4 MSA [6] Multiple size adaptation Linear Software size(s) 5 RTM [7] Regression towards the mean Linear Software size 6 AQUA [8] Similarity-based adaptation Linear All features 7 GA [9] Adaptation based on Linear All features Genetic algorithm 8 NNet [10] Non-linear adaptation Non-linear All features based on Neural network observation, suggested that an effort adaptation using only a software size variable is rational, because any size variables are always strongly correlated with the effort. Furthermore, adjusting the effort using a size variable also allows an estimation to scale the estimated effort value between pairs of analogues based on differences in size.…”

Section: Solution Adaptation Techniques For Abementioning

confidence: 99%

See 1 more Smart Citation

LSA-X: Exploiting Productivity Factors in Linear Size Adaptation for Analogy-Based Software Effort Estimation

Phannachitta

Monden

Keung

et al. 2016

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYAnalogy-based software effort estimation has gained a considerable amount of attention in current research and practice. Its excellent estimation accuracy relies on its solution adaptation stage, where an effort estimate is produced from similar past projects. This study proposes a solution adaptation technique named LSA-X that introduces an approach to exploit the potential of productivity factors, i.e., project variables with a high correlation with software productivity, in the solution adaptation stage. The LSA-X technique tailors the exploitation of the productivity factors with a procedure based on the Linear Size Adaptation (LSA) technique. The results, based on 19 datasets show that in circumstances where a dataset exhibits a high correlation coefficient between productivity and a related factor (r ≥ 0.30), the proposed LSA-X technique statistically outperformed (95% confidence) the other 8 commonly used techniques compared in this study. In other circumstances, our results suggest using any linear adaptation technique based on software size to compensate for the limitations of the LSA-X technique.

show abstract

Section: Gacontrasting

confidence: 68%

Section: Solution Adaptation Techniques For Abementioning

confidence: 99%

LSA-X: Exploiting Productivity Factors in Linear Size Adaptation for Analogy-Based Software Effort Estimation

Phannachitta

Monden

Keung

et al. 2016

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

“…Chiu and Huang (2007), Cirilovic, Vajdic, Mladenovic, and Queiroz (2014), Dejaneger et al (2012), Finnie et al (1997), Huang, Chiu, and Chen (2008), Kim, An, and Kang (2004), Park and Baek (2008), Shehab, Farooq, Sandhu, Nguyen, and Nasr (2010), and Zhang, Fuh, and Chan (1996 all utilize the logistic sigmoid function. However, we discover that other neural network techniques are used.…”

Section: Artificial Neural Networkmentioning

confidence: 99%

An Investigation of Nonparametric Data Mining Techniques for Acquisition Cost Estimating

Brown¹,

White²

2017

Defense ARJ

View full text Add to dashboard Cite

The Department of Defense (DoD) cost estimating methodology traditionally focuses on parametric estimating using ordinary least squares (OLS) regression. Given the recent advances in acquisition data collection, however, senior leaders have expressed an interest in incorporating "data mining" and "more innovative analyses" within cost estimating. Thus, the goal of this research is to investigate nonparametric data mining techniques and their application to DoD cost estimating. Using a meta-analysis of 14 cost estimating studies containing 32 datasets that predominantly relate to commercial software development, the predictive accuracy of OLS regression is measured against three nonparametric data mining techniques. The meta-analysis results indicate that, on average, the nonparametric techniques outperform OLS regression for cost estimating. Follow-on data mining research that incorporates DoD-specific acquisition cost data is recommended to extend this article's findings.

show abstract

“…To measure the similarity between pairs of projects, distance metrics are used. Euclidean (Jeffery et al, 2000), Manhattan (Emam et al, 2001) and Minkowski distances (Stamelos et al, 2003) are the widely used distance metrics in analogy-based estimations, [14]. Various researches have been done to improve the estimation accuracy in analogy -based estimations.…”

Section: Related Workmentioning

confidence: 99%

“…The author Chiu, et.al. [14], proposed an adjusted analogy-based software effort estimation model by adopting the GA method to adjust the effort based on the similarity distances. In other words, the effort of the closest project is not used directly, but it is adjusted to improve the accuracy.…”

Section: Related Workmentioning

confidence: 99%

Software Effort Prediction using Statistical and Machine Learning Methods

Malhotra¹,

Jain²

2011

IJACSA

View full text Add to dashboard Cite

-Accurate software effort estimation is an important part of software process. Effort is measured in terms of person months and duration. Both overestimation and underestimation of software effort may lead to risky consequences. Also, software project managers have to make estimates of how much a software development is going to cost. The dominant cost for any software is the cost of calculating effort. Thus, effort estimation is very crucial and there is always a need to improve its accuracy as much as possible. There are various effort estimation models, but it is difficult to determine which model gives more accurate estimation on which dataset. This paper empirically evaluates and compares the potential of Linear Regression, Artificial Neural Network, Decision Tree, Support Vector Machine and Bagging on software project dataset. The dataset is obtained from 499 projects. The results show that Mean Magnitude Relative error of decision tree method is only 17.06%. Thus, the performance of decision tree method is better than all the other compared methods.

show abstract

The adjusted analogy-based software effort estimation based on similarity distances

Cited by 161 publications

References 27 publications

LSA-X: Exploiting Productivity Factors in Linear Size Adaptation for Analogy-Based Software Effort Estimation

LSA-X: Exploiting Productivity Factors in Linear Size Adaptation for Analogy-Based Software Effort Estimation

An Investigation of Nonparametric Data Mining Techniques for Acquisition Cost Estimating

Software Effort Prediction using Statistical and Machine Learning Methods

Contact Info

Product

Resources

About