Figure 1 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Source publication
Software Cost Estimation (SCE) is an integral part of pre-development stage of software project with a target to accomplish a better visibility towards possible risk while gaining more information towards reaching success rate to meet the deadline of delivery. Irrespective of multiple research contribution model towards SCE, the problem and challen...
Contexts in source publication
Context 1
... standard term cost is usually represented in the form of resources engaged in the development, time consumed in development, and all cumulative approximated effort to accomplish the complete development stage. A typical cost estimation practice is shown in Fig.1, where the project manager defines the target software cost. ...
Context 2
... the same time, this process is followed up by manipulation of various attributes and sizes until the cost of the target software is found justified. The process exhibited in Fig.1 is highly essential to perform analysis and forecasting of all possible risks involved in costing and realize various trade-offs and sensitivities associated with it. This process lets the project manager scrutinize the software project and filter out the evaluated risk possibilities to accomplish the cost of the target software. ...
Context 3
... should be noted that the process mentioned above of software cost estimation is carried out by the project manager and equally contributed by different teams working for testing, development, and architecture. Further, it can be seen from Fig.1 that there are varied inputs for cost estimation, viz. ...
Context 4
... can be carried out through the common interface module constructed in the front end handled by the estimator/stakeholder of software projects. Computed values of PC is shown in Fig.10 where it can be seen that proposed OLCE has excelled with superior accuracy compared to all existing scheme frequently adopted for SCE. ...
Citations
... [4] Figure 1: The typical process of Software Cost Estimation [4] The process shown in Figure 1 is a critical practice to perform analysis and predict all the possible risks and trade-offs in the costing procedure. This process gives the software project manager the possibility to investigate the software project and filter out the evaluated risk possibilities to accomplish the cost of the target software. ...
... It further retains the best outcome while parents are selected to generate an outcome that is further used for scoring and scaling the population. In all the abovementioned steps of operation, the scheme follows three core rules to finetune the outcome of the population: [4] • Rule for Selection: The main principle that selects the individual referred to as the parent, resulting in a modified population in successive rounds of operation. • Rule for Aggregation: This is the second principle that generates an updated population by merging information from two parents. ...
... To understand the unique features of their proposed scheme, Figure 6 will elaborate on the operation of the working in comparison to the conventional technique. [4] In the third research paper, an Artificial Neural Network with Neuro-Evolution of Augmenting Topology is proposed. Artificial Neural Networks (ANNs) are a type of Machine Learning model inspired by the structure and function of the human brain. ...
Software Cost Estimation (SCE) is one of the most vital parts when starting a new software engineering project; it helps with allocating resources, managing risks, making informed decisions, and stands in correlation with the success or the failure of a project. Because Software Cost Estimation (SCE) is prone to human bias, solutions started being researched with the aid of Artificial Intelligence (AI) and Machine Learning (ML). This paper will investigate the importance of Software Cost Estimation (SCE). Further, the existing taxonomies and methodologies regarding using neural networks with Software Cost estimation will be compared (COCOMO, GEHO-ANN, OLCE, and -ANN-NEAT). This will be done using evaluation metrics such as RMSE, MMRE, PRED, MAE, etc. After, further research is proposed on why using Deep Reinforcement Learning (DRL) could be very beneficial for developing Software Cost Prediction Models. This technique combines Deep Learning (DL) and Machine Learning (ML) and can solve complex tasks with many variables and a rapidly developing environment.KeywordsSoftware Cost EstimationArtificial IntelligenceMachine LearningDeep Reinforcement LearningNeural Networks
... As a result of the research, OLCE demonstrated approximately 73% accuracy and 50% faster response time than existing models that are said to be adopted for SCE. It can therefore be concluded that OLCE is a cost-effective and accurate method for SCE [11]. ...
The IT industry has faced many challenges related to software effort and cost estimation. A cost assessment is conducted after software effort estimation, which benefits customers as well as developers. The purpose of this paper is to discuss various methods for the estimation of software effort and cost in the context of software engineering, such as algorithmic methods, expert judgment methods, analogy-based estimation methods, and machine learning methods, as well as their different aspects. In spite of this, estimation of the effort involved in software development are subject to uncertainty. Several methods have been developed in the literature for improving estimation accuracy, many of which involve the use of machine learning techniques. A machine learning framework is proposed in this paper to address this challenging problem. In addition to being completely independent of algorithmic models and estimation problems, this framework also features a modular architecture. It has high interpretability, learning capability, and robustness to imprecise and uncertain inputs.
