Improving the Accuracy of Software Effort Estimation Based on Multiple Least Square Regression Models by Estimation Error-Based Data Partitioning

Purpose The study aims to investigate the application of the data element market in software project management, focusing on improving effort estimation by addressing challenges faced by traditional methods. Design/methodology/approach This study proposes a solution based on feature selection, utilizing the data element market and reinforcement learning-based algorithms to enhance the accuracy of software effort estimation. It explores the application of the MARLFS algorithm, customizing improvements to the algorithm and reward function. Findings This study demonstrates that the proposed approach achieves more precise estimation compared to traditional methods, leveraging feature selection to guide project management in software development. Originality/value This study contributes to the field by offering a novel approach that com-bines the data element market, machine learning, and feature selection to improve software effort estimation, addressing limitations of traditional methods and providing insights for future research in project management.

Over the past ten couple of years, there is a variety of effort models proposed by academicians and practitioners at early stage of software development life cycle. Some addressed that efforts could be predicted using Lines of Codes(LOC) and COCOMO, others emphasized that it could be made using Function Point Analysis(FPA) or others. The study seeks to develop a model that estimates software effort by studying and analyzing small and medium scale application software. To develop such a model, 50 completed software projects are collected from a software company. With the sample data, design team factors are identified and extracted. By applying them to simple regression analyses, a prediction of software of effort estimates with accuracy of MMRE = 9% was constructed. The results give several benefits. First, the estimation problems are minimized due to the simple procedure used in identifying those factors. Second, the predicted software projects are only limited to a specific environment rather than being based upon industry environment. We believe the accuracy of effort estimates can be improved. According to the results analyzed, the work shows that it is possible to build up simple and useful prediction model based on data extracted at the early stage of software development life cycle. We hope this model can provide valuable ideas and suggestions for project designers for planning and controlling software projects in near future.

Constructive Cost Model II (COCOMO II) is investigated as the most popular model for software cost estimation. COCOMO II depends on several variables or Cost Drivers (CD). This research investigates the role of Effort Multiplier (EM) and Line of Code (LOC) to improve the accuracy of cost estimation. Fuzzy Logic has been implemented to the COCOMO II to represent the EM. Furthermore, in order to produce better estimation, this research uses Gaussian Membership Function to redesign the Effort Multiplier by studying the behavior of COCOMO II. This research also applies Neural Network (NN) approach to increase the accuracy of software effort estimation by training the software development datasets. The result is proposed model gives contribution to decrease error significantly.

Effort estimations are a crucial aspect of software development. The tasks should be completed before the start of any software project. Accurate estimations increase the chances of project success, and inaccurate information can lead to severe issues. This study systematically reviewed the literature on effort-estimating models from 2015-2024, identifying 69 relevant studies from various publications to compile information on various software work estimation models. This review aims to analyze the models proposed in the literature and their classification, the metrics used for accuracy measurement, the leading model that has been chiefly applied for effort estimation, and the benchmark datasets available. The study utilized 542 relevant articles on software development, cost, effort, prediction, estimation, and modelling techniques in the search strategy. After 194 selections, the authors chose 69 articles to understand ML applications in SEE comprehensively. The researchers used a scoring system to assess each study’s responses (from 0 to 5 points) to their research questions. This helped them identify credible studies with higher scores for a comprehensive review aligned with its objectives. The data extraction process identified 91% (63) of 69 studies as either highly or somewhat relevant, demonstrating a successful search strategy for analysis. The literature review on SEE indicates a growing preference for ML-based models in 59% of selected studies. 17% of the studies chosen favor hybrid models to overcome software development challenges. We qualitatively analyzed all the literature on software effort estimation using expert judgment, formal estimation techniques, ML-based techniques, and hybrid techniques. We discovered that researchers have frequently used ML-based models to estimate software effort and are currently in the lead. This study also explores the application of feature importance and selection in machine learning models for Software Effort Estimation (SEE) using popular algorithms like support Vector Machine (SVM), AdaBoost (AB), Gradient Boost (GB), and Random Forest (RF) with six benchmark datasets like CHINA, COCOMO-NASA2, COCOMO, COCOMO81, DESHARNAIS, and KITCHENHAM. We analyze the dataset descriptions and feature importance of the dataset analysis using ML models for choosing crucial play attributes in SEE.

<i>Introduction</i>: The precise estimation of software effort is a significant difficulty that project managers encounter during software development. Inaccurate forecasting leads to either overestimating or underestimating software effort, which can be detrimental for stakeholders. The International Function Point Users Group&#x2019;s Function Point Analysis (FPA) method is one of the most critical methods for software effort estimation. However, the practice of using the FPA method in the same fashion across all software areas needs to be reexamined. <i>Aim</i>: We propose a model for evaluating the influence of data clustering on software development effort estimation and then finding the best clustering method. We call this model the effort estimation using machine learning applied to the clusters (EEAC) model. <i>Method</i>: We cluster the dataset according to the clustering method and then apply the FPA and EEAC methods to these clusters for effort estimation. The clustering methods we use in this study include five categorical variable criteria (Development Platform, Industrial Sector, Language Type, Organization Type, and Relative Size) and the k-means clustering algorithm. <i>Results</i>: The experimental results show that the estimation accuracy obtaining with clustering consistently outperforms the accuracy without clustering for both the FPA and EEAC methods. Significantly, using the FPA method, the average improvement rate from using clustering as opposed to non-clustered was highest at 58.06%, according to the RMSE. With the EEAC method, this number reached 65.53%. The Industry Sector categorical variable achieves the best accuracy estimation compared to the other clustering criteria and k-means clustering. The improvement in accuracy in terms of the RMSE when applying this criterion is 63.68% for the FPA method and 72.02% for the EEAC method. <i>Conclusion</i>: Better results are obtained through dataset clustering compared to no clustering for both the FPA and EEAC methods. The Industry Sector is the most suitable clustering method among the tested clustering methods.

In the life cycle of software product development, the software effort estimation (SEE) has always been a critical activity. The researchers have proposed numerous estimation methods since the inception of software engineering as a research area. The diversity of estimation approaches is very high and increasing, but it has been interpreted that no single technique performs consistently for each project and environment. Multi-criteria decision-making (MCDM) approach generates more credible estimates, which is subjected to expert’s experience. In this paper, a hybrid model has been developed to combine MCDM (for handling uncertainty) and machine learning algorithm (for handling imprecision) approach to predict the effort more accurately. Fuzzy analytic hierarchy process (FAHP) has been used effectively for feature ranking. Ranks generated from FAHP have been integrated into weighted kernel least square support vector machine for effort estimation. The model developed has been empirically validated on data repositories available for SEE. The combination of weights generated by FAHP and the radial basis function (RBF) kernel has resulted in more accurate effort estimates in comparison with bee colony optimisation and basic RBF kernel-based model.

Accurate software effort estimation has a big importance for software companies for the reason that management of the project, control of the project, financial matters and timely deliveries are achieved with effort estimation. Thus, effort estimation plays vital role for software companies. In this study, software effort estimation is predicted by using Multilayer Perceptron and Adaptive Neuro Fuzzy Inference System. As a dataset, NASA 93 with 93 projects and Desharnais with 77 projects are used. The results show that Mean Magnitude Relative Error of Adaptive Neuro Fuzzy Inference System is lower than Multilayer Perceptron. In addition, it is seen that PRED(0.25) value of Adaptive Neuro Fuzzy Inference System is higher than Multilayer Perceptron. Thus, performance of Adaptive Neuro Fuzzy Inference System is better when compared to performance of Multilayer Perceptron.

Prediction of software development is the key task for the effective management of any software industry. The accuracy and reliability of the prediction mechanisms used for the estimation of software development effort is also important. A series of experiments are conducted to gradually progress towards the improved accurate estimation of the software development effort. However, while conducting these experiments, it was found that the size of the training set was not sufficient to train a large and complex artificial neural network (ANN). To overcome the problem of the size of the available training data set, a novel multilayered architecture based on a neural network model is proposed. The accuracy of the proposed multi-layered model is assessed using different criteria, which proves the pre-eminence of the proposed model.

Accurate software effort estimation is a persistent challenge in project management, as a significant share of project failures is attributed to inadequate prior risk consideration. Among the widely adopted methodologies that are used for early estimation of the success of a project is the Use Case Points (UCP) method, yet its framework does not take into consideration risk factors, undermining its reliability. To improve upon this limitation, this study introduces UCPRisk, a rule-based expert-guided UCP model that explicitly integrates risk factors across six dimensions: requirements, planning and control, project complexity, user involvement, team dynamics, and organizational environment. The model was evaluated through three public service application case studies, producing effort estimates of 1,564.42 man-hours (agriculture application), 7,287.91 man-hours (company registration), and 4,669.17 man-hours (industrial permit registration). Compared to traditional UCP, UCPRisk reduced the average Relative Error (RE) to 24.3%, demonstrating improved alignment with actual project outcomes. While not a definitive cost calculation tool, UCPRisk provides a structured framework that embeds risk into early estimation, offering more realistic projections for software development.

Accurate effort estimation in early stage of software development life cycle is a major challenge for many software industries. The use of various optimization techniques helps in improving the effort estimation accuracy. The Support Vector Regression (SVR) is one of different soft-computing techniques, that helps in getting optimal estimated values. The idea of SVR is based upon the computation of a linear regression function in a high dimensional feature space where the input data are mapped via a nonlinear function. Further, the SVR kernel methods can be applied in transforming the input data and then based on these transformations, an optimal boundary between the possible outputs can be obtained. The main objective of the research work carried out in this paper is to estimate the software effort using class point approach. Then, an attempt has been made to optimize the results obtained from class point analysis using various SVR kernel methods to achieve better prediction accuracy. A performance comparison of the models obtained using various SVR kernel methods has also been presented in order to highlight performance achieved by each method.

Background: Developing and maintaining a software effort estimation (SEE) data set within a company (within data) is costly. Often times parts of data may be missing or too difficult to collect, e.g. effort values. However, information about the past projects-although incomplete- may be helpful, when incorporated with the SEE data sets from other companies (cross data).Aim: Utilizing cross data to aid within company estimates and local experts; Proposing a synergy between semi-supervised, active and cross company learning for software effort estimation.Method: The proposed method: 1) Summarizes existing unlabeled within data; 2) Uses cross data to provide pseudo-labels for the summarized within data; 3) Uses steps 1 and 2 to provide an estimate for the within test data as an input for the local company experts. We use 21 data sets and compare the proposed method to existing state-of-the-art within and cross company effort estimation methods subject to evaluation by 7 different error measures.Results: In 132 out of 147 settings (21 data sets X 7 error measures = 147 settings), the proposed method performs as well as the state-of-the-art methods. Also, the proposed method summarizes the past within data down to at most 15% of the original data.Conclusion: It is important to look for synergies amongst cross company and within-company effort estimation data, even when the latter is imperfect or sparse. In this research, we provide the experts with a method that: 1) is competent (performs as well as prior within and cross data estimation methods) 2) reflects on local data (estimates come from the within data); 3) is succinct (summarizes within data down to 15% or less); 4) cheap (easy to build).

Software cost and time estimation is the process of estimating the cost and time required to develop a software system. Software cost and time estimation supports the planning and tracking of software projects. Effectively controlling the expensive investment of software development is one of the important issues in software project management. Estimating software development cost with high precision is still a great challenge for project managers, because it allows for considerable financial and strategic planning. Software cost estimation refers to the predictions of the likely amount of effort, time, and staffing levels required to build a software system. A very helpful form of cost estimation is the one made at an early stage during a project, when the costing of the project is proposed for approval. However, estimates at the early stages of the development are the most difficult to obtain. In this paper a novel Constructive Cost Model (COCOMO) based on soft computing approach is proposed for software cost estimation. This model carries some of the desirable features of neural networks approach, such as learning ability and good interpretability, while maintaining the merits of the COCOMO model. Unlike the standard neural networks approach, the proposed model can be interpreted and validated by experts, and has good generalisation capability. The model deals effectively with imprecise and uncertain input and enhances the reliability of software cost estimates. From the experimental results, it was concluded that, by the proposed neural network model, the accuracy of cost estimation can be improved and the estimated cost can be very close to the actual cost.

Software development effort estimation is one of the most crucial activities in software engineering. Effort estimation permits managers and software engineers to anticipate, forecast, and precisely quote the schedule, budget and manpower requirements. By accurately estimating the effort; software projects can be saved from under run or over run. In this paper we have summarized and then analyzed the past work of software effort estimation in a systematic way. 10 researches were surveyed and explained briefly that how they are contributing towards solving the effort estimation problem in terms of time, cost or test. It also emphasizes that various effort estimation models have different pros and cons and can be used in different context on basis of different types of historical data. The survey discovered the most popular models used for effort prediction are supervised learning algorithms. The trends identified through this survey can help in exploring the potential research areas.

Software effort estimation is a crucial phase in software project management. Accuracy of estimation directly affects project success or failure. Managers try to estimate proper effort resources and this is a challenging issue for management. Having a set of tools and methodologies, estimation process can be made better. COCOMO is one of the most used model which has a parametric form. Also, artificial neural networks (ANN) are combined with COCOMO and these methods increased overall performance. However, effort estimation process generally produces one output; estimation value. It is a well-known issue that a project manager must keep in the mind that any estimation must have some upper and lower limits, boundaries. In this paper, a novel method, combining COCOMO used ANN with K-Means is used to estimate effort and possible boundaries. ANN output is used as input to K-Means sets and proper set value is calculated, including possible lower and upper effort estimation value. Experimental results are shown that proposed method has acceptable results over ANN and COCOMO.

Voluntary effort combined with functional electrical stimulation (FES) can improve post-stroke motor recovery, yet it is important for the user to actively engage in the rehabilitation task rather than reduce effort during FES assistance, which is an undesired phenomenon known as 'slacking'. To prevent slacking, EMG (electromyography)-controlled FES devices provide assistance as a function of voluntary paretic limb effort that is estimated from paretic muscle EMG using filters that remove stimulation-related responses (m-Waves). However, existing effort estimation methods do not compensate for the reduction of paretic muscle EMG due to interaction of voluntary action potentials with stimulus generated action potentials in the same motor axons, known as 'occlusion'. This phenomenon can lead to undesirable underestimation of voluntary effort during FES applications. In this study, we recruited five people without stroke to investigate the hypothesis that occlusion can be measured using a novel finger extension force tracking task and be used to improve voluntary effort estimation. We evaluated 1) the accuracy of voluntary effort estimation with and without occlusion correction and 2) characterized the effect of different m-Wave filters (Gram-Schmidt and comb filters) on effort estimation accuracy. Results indicated that occlusion correction can significantly improve accuracy of voluntary effort estimated from EMG and that the choice of m-Wave filters can significantly affect effort estimation accuracy.Clinical relevance- This study aims to improve EMG-based effort estimation of functional electric stimulation (FES) rehabilitation participants after stroke. This is critical for 'slacking' reducing FES applications, which have a potential to enhance the efficacy of FES therapy.