Reliable Confidence Intervals for Software Effort Estimation

2010

Software cost estimation is one of the prerequisite managerial activities carried out at the software development initiation stages and also repeated throughout the whole software life-cycle so that amendments to the total cost are made. In software cost estimation typically, a selection of project attributes is employed to produce effort estimations of the expected human resources to deliver a software product. However, choosing the appropriate project cost drivers in each case requires a lot of experience and knowledge on behalf of the project manager which can only be obtained through years of software engineering practice. A number of studies indicate that popular methods applied in the literature for software cost estimation, such as linear regression, are not robust enough and do not yield accurate predictions. Recently the dual variables Ridge Regression (RR) technique has been used for effort estimation yielding promising results. In this work we show that results may be further improved if an AI method is used to automatically select appropriate project cost drivers (inputs) for the technique. We propose a hybrid approach combining RR with a Genetic Algorithm, the latter evolving the subset of attributes for approximating effort more accurately. The proposed hybrid cost model has been applied on a widely known high-dimensional dataset of software project samples and the results obtained show that accuracy may be increased if redundant attributes are eliminated.

Effort Estimation (EE) is a technique for finding the entire effort required to predict the accuracy of a model. It's a significant chore in software application development practice. To find accurate estimation, numerous predictive models have developed in recent times. The estimate prepared during the early stage of a model expansion is inaccurate since requirements at that time are not very clear, but as the model progresses, the accuracy of the estimation increases. Therefore, accurate estimation is essential to choose for each software application model development. Here, Linear Regression (LR), Multi-layer perceptron (MLP), Random Forest (RF) algorithms are implemented using WEKA toolkit, and results shows that Linear Regression shows better estimation accuracy than Multilayer Perceptron and Random Forest.

IEEE access, 2024

The average software company spends a huge amount of its revenue on R&D for how to deliver software on time. Accurate software effort estimation is critical for successful project planning, resource allocation, and on-time delivery within budget for sustainable software development. However, both overestimation and underestimation pose significant challenges in software development, necessitating continuous improvement in estimation techniques. This study reviews recent machine learning approaches exploited to enhance software effort estimation (SEE) accuracy, focusing on research published between 2020 and 2023. The literature review employed an approach to identify pertinent research on machine learning techniques for software estimation efforts. Additionally, comparative experiments were conducted employing five commonly used ML methods: K-Nearest Neighbor, Support Vector Machine, Random Forest, Logistic Regression, and LASSO Regression. These techniques were assessed using five widely employed accuracy metrics such as Mean Squared Error (MSE), Mean Magnitude of Relative Error (MMRE), R-squared, Root Mean Squared Error (RMSE), and Mean Absolute Percentage Error (MAPE) on seven benchmark datasets (Albrecht, Desharnais, China, Kemerer, Mayazaki94, Maxwell, COCOMO). By carefully reviewing study quality, analyzing results across the literature, and rigorously evaluating experimental outcomes, clear conclusions were drawn about the most promising techniques for achieving state-of-the-art accuracy in estimating software effort. This study makes three key contributions to the field: firstly, it furnishes a thorough overview of recent machine learning research in software effort estimation (SEE); secondly, it provides data-driven guidance for researchers and practitioners to select optimal methods for accurate effort estimation; and thirdly, it demonstrates the performance of publicly available datasets through experimental analysis. Enhanced estimation supports the development of better predictive models for software project time, cost, and staffing needs. The findings aim to focus future research directions and tool development toward the most accurate machine learning approaches for modeling software development effort, costs, and delivery schedules.

SSRN Electronic Journal, 2022

Software estimation is one of the pivotal activities in software engineering projects. However, predicting effort is challenging due to the complexity, intangibility, and diversity of software solutions and their involved expertise and applied technologies. This work aims at improving the accuracy of software estimation using regression algorithms and based on the Use-Case Points analysis (UCP). Five regression algorithms were applied including Random Forests, Stochastic Gradient Decent (SGD), K-Nearest Neighbour (KNN), Support Vector Machine (SVM), and Neural Networks (NN). These algorithms were applied to a historical dataset that represents several object-oriented software projects. The dataset consists of 70 projects that are described using 37 attributes which are related to software requirement specifications, development process, and domain application in addition to a set of technical and environmental factors. The experimental results in this work showed that Random Forests and SGD algorithms were successful in achieving significant improvement in the predicting software effort estimation compared to Use-Case Point analysis. The random forest model scored 0.86 in R2 , while the SGD model scored 0.83. It was concluded that regression improves software effort prediction compared to other estimation methods, particularly if adequate data is collected, processed, and analysed using the right algorithms.

International Journal of Advanced Computer Science and Applications, 2021

This project involves research about software effort estimation using machine learning algorithms. Software cost and effort estimation are crucial parts of software project development. It determines the budget, time and resources needed to develop a software project. One of the well-established software project estimation models is Constructive Cost Model (COCOMO) which was developed in the 1980s. Even though such a model is being used, COCOMO has some weaknesses and software developers still facing the problem of lack of accuracy of the effort and cost estimation. Inaccuracy in the estimated effort will affect the schedule and cost of the whole project as well. The objective of this research is to use several algorithms of machine learning to estimate the effort of software project development. The best machine learning model is chosen to compare with the COCOMO.

Journal of Network and Information Security, 2017

Effective software project estimation is one of the most challenging and important activities in software development. Proper project planning and control is not possible without a sound and reliable estimate. As a whole, the software industry doesn't estimate projects well and doesn't use estimates appropriately. We suffer far more than we should as a result and we need to focus some effort on improving the situation. Effort estimation is important to minimize the cost of a software project. The existing situation may lead to serious consequences to the company as because of poor effort estimation a major percentage of the project turns out to be either more expensive than expected, late on deliver and many more issues. Not properly giving importance to the effort estimation task by under-staffing it, running the task of low quality deliverables and setting too short schedule resulting in loss of credibility as deadlines are missed always lead to problems. The current system available for effort estimation produces non-comprehensible results. Hence the purpose of this project is to produce a software system which produces a more accurate and comprehensible results using modern tools and make it easier for the project manager to easily identify the effort needed to complete a software project in terms size of project, cost etc. The various algorithm used are Support vector machine(SVM) which are best for both classification and regression and an Active Learning Based Approach (ALBA)for rule extraction from the output of SVM to produce a comprehensible output for rule.

International Journal of Software Engineering & Applications, 2020

As demand for computer software continually increases, software scope and complexity become higher than ever. The software industry is in real need of accurate estimates of the project under development. Software development effort estimation is one of the main processes in software project management. However, overestimation and underestimation may cause the software industry loses. This study determines which technique has better effort prediction accuracy and propose combined techniques that could provide better estimates. Eight different ensemble models to estimate effort with Ensemble Models were compared with each other base on the predictive accuracy on the Mean Absolute Residual (MAR) criterion and statistical tests. The results have indicated that the proposed ensemble models, besides delivering high efficiency in contrast to its counterparts, and produces the best responses for software project effort estimation. Therefore, the proposed ensemble models in this study will help the project managers working with development quality software.

IEEE ACCESS, 2024

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.

2017

Accurate Software Effort Estimation is vital to the areas of Software Project Management. It is a process to predict the Effort in terms of cost and time, required to develop a software product. Traditionally, researchers have used the off the shelf empirical models like COCOMO or developed various methods using statistical approaches like regression and analogy based methods but these methods exhibit a number of shortfalls. To predict the effort at early stages is really difficult as very less information is available. To improve the effort estimation accuracy, an alternative is to use machine learning (ML) techniques and many researchers have proposed plethora of such machine learning based models. This paper aims to systematically analyze various machine learning models considering the traits like type of machine learning method used, estimation accuracy gained with that method, dataset used and its comparison with empirical model. Although researchers have started exploring Mach...

Abstract The importance of Software Cost Estimation at the early stages of the development life cycle is clearly portrayed by the utilization of several algorithmic and artificial intelligence models and methods, appeared so far in the literature. Despite the several comparison studies, there seems to be a discrepancy in choosing the best prediction technique between them. Additionally, the large variation of accuracy measures used in the comparison procedure constitutes an inhibitory factor which complicates the decision-making.