A Review Article on Software Effort Estimation in Agile Methodology

Abstract

Currently, Agile software development method has been commonly used in software development projects, and the success rate is higher than waterfall projects. The effort estimation in Agile is still a challenge because most existing means are developed based on the conventional method. Therefore, this study aimed to ascertain the software effort estimation method that is applied in Agile, the implementation approach, and the attributes that affect effort estimation. The results showed the top three estimation that is applied in Agile, are machine learning (37%), Expert Judgement (26%), and Algorithmic (21%). The implementation of all machine learning methods used a hybrid approach, which is a combination of machine learning and expert judgement, or a mix of two or more machine learning. Meanwhile, the implementation of effort estimation through a hybrid approach was only used in 47% of relevant articles. In addition, effort estimation in Agile involved twenty-four attributes, where Complexity, Experience, Size, and Time are the most commonly used and implemented.

Significant Factors in Agile Software Development of Effort Estimation

“…Effort estimation is a crucial part of ASD for three reasons: 1) maximize project velocity; 2) optimize individual developer effort across multiple projects; 3) optimal scheduling to achieve global efficiencies (Malgonde & Chari, 2019). However, most of the effort estimation method used in ASD is the expert judgment method, especially the Planning Poker technique (Sudarmaningtyas & Mohamed, 2021).…”

“…An indicator is in the form of a single variable used in conjunction with one or more variables to form a composite measure, where each indicator has attributes. Attributes embedded in indicators are complexity and size because these attributes mostly used agile effort estimation in the last three years (Fernandez-Diego et al, 2020;Sudarmaningtyas & Mohamed, 2021). All constructs, indicators, and attributes used in the questionnaire are briefly described in Table 5, and the questionnaire used to collect data is entirely served in Appendix 1.…”

“…The Planning Poker technique is a part of the expert judgment method most implemented in Agile. Although this technique is in accordance with Agile characteristics, the result has shown biased value (Sudarmaningtyas & Mohamed, 2021). In addition, these methods heavily rely on the estimator experience and rarely involve other factors in the process of estimation.…”

Preliminary Estimation for Software Development Projects Empowered with a Method of Recommending Optimal Duration and Team Composition

“…Another widely used method, PERT [3,4], is relatively easy but does not take into account the agile nature of modern software development projects. Agile-oriented methods like planning poker, T-shirt sizing, affinity grouping, and their variations are rather applicable by agile teams at the implementation stage [5][6][7][8]. A common downside of the existing methods (except COCOMO II) is that they do not cover the whole software development life cycle starting from project ideation and ending with production, including maintenance and support.…”

Real-time Estimation Approach to Scrum Projects Effort: Task Point and Individual Reliability (S)

“…In [10] [11], machine learning was used for estimation. What's more, the authors in [10] compared machine learning, expert opinions and mathematical algorithm models, finally concluding that machine learning is more accurate in Agile estimation; By analyzing the text of user story description, Sudarmaningtyas and Mohamed [10] got 83% accuracy of story point estimation. In [12], the effort of Scrum-based IT projects was estimated with the usage of fuzzy logic model.…”