Software Project Effort Estimation Research Articles

Comparing Stacking Ensemble and Deep Learning for Software Project Effort Estimation

This study focuses on improving the accuracy of effort estimation by employing ensemble, deep learning, and transfer learning techniques. An ensemble approach is utilized, incorporating XGBoost, Random Forest, and Histogram Gradient Boost as generators to enhance predictive capabilities. The performance of the ensemble method is compared against both the deep learning approach and the PFA-IFPUG technique. Statistical criteria including MAE, SA, MMRE, PRED(0.25), MBRE, MIBRE, and relevant information related to MMRE and PRED(0.25) are employed for evaluation. The results demonstrate that combining regression models with Random Forest as the final regressor and XGBoost and Histogram Gradient Boost as prior generators yields more accurate effort estimation than other combinations. Furthermore, the findings highlight the potential of transfer learning in the deep learning method, which exhibits superior performance over the ensemble approach. This approach leverages pre-trained models and continuously improves performance by training on new datasets, providing valuable insights for cross-company and cross-time effort estimation problems. The ISBSG dataset is used to build the pre-trained model, and the inductive transfer learning approach is verified based on the Desharnais, Albrecht, Kitchenham, and China datasets. The study underscores the significance of transfer learning and the integration of domain-specific knowledge from existing models to enhance the performance of new models, thereby improving accuracy, reducing errors, and enhancing predictive capabilities in effort estimation.

An optimized case-based software project effort estimation using genetic algorithm

Software development companies have long suffered from inaccurate estimation of their software projects. This in turn led to huge losses, especially in the financial resources available for the project as well as the time required to complete it. As a result of this, the research community has developed different methods for estimating effort in software projects in the hope of achieving high levels of accuracy and efficiency in the use of available resources. Among those methods that have proven to be accurate in estimating the effort of software projects is the use of machine learning (ML) techniques, especially the case-based reasoning technique (CBR). This technique is based on adapting previously successful solutions for similar software projects. However, the CBR technique suffers from a problem which is its multiple parameters that are difficult to be tuned. This justifies the importance of the adaptation and adjustment process as an essential part of CBR to produce accurate and efficient results with least absolute estimation error. In this paper, one of the most efficient multi-objective evolutionary techniques, the Genetic Algorithm (GA), are used to help find the best set of classical CBR parameters (feature selection, feature weighting, similarity measures, and k number of nearest neighbors) to produce the most accurate effort estimates for software projects. The proposed CBR-GA model showed the effectiveness of using the GA algorithm to search for the best combination of CBR parameters and thus improve its accuracy. This in turn is beneficial for project managers in the early financial planning phase for effort estimation and thus project cost control. To validate the proposed CBR-GA model, we used a set of public benchmark datasets available on PROMISE data repository, in addition we used a set of reliable evaluation metrics. The obtained results are promising in terms of accuracy and significance tests. This implies the importance of search-based techniques for tuning effort estimation methods.

Modeling of software project effort estimation: a comparative performance evaluation of optimized soft computing-based methods

Modeling of software project effort estimation: a comparative performance evaluation of optimized soft computing-based methods

An Optimized Neuro-Fuzzy Network for Software Project Effort Estimation

Estimating software effort is an essential project management practice. The software effort estimation is the process of predicting the time and efforts required in the development of software projects. Estimating software cost is a critical challenge during the planning stage. Due to the lack of availability of quality data and the dynamic nature of software development, accurate estimation is difficult. This paper proposes an efficient software cost estimation method for the Genetic Elephant Herding Optimization-based Neuro-Fuzzy Network (GEHO-based NFN). In this method, a neuro-fuzzy network (NFN) is used to predict the software efforts in terms of cost. The training of this NFN is optimized using the genetic elephant herding optimization (GEHO) method, which combines the features of the genetic algorithm (GA) and the elephant herding optimization (EHO) techniques. The performance of the developed method was evaluated using five historical & benchmark datasets from the industrial projects. These are based on the four widely used performance evaluation metrics, such as Mean magnitude of relative Error (MMRE), Median magnitude of relative error (MdMRE), Root Mean Square Error (RMSE), and Prediction Accuracy (PRED). The Comparative analysis and experimental results of the proposed method conclude that the performance of the GEHO-based NFN method is better than other popular soft computing methods like Linear regression, Support Vector Regression (SVR), Wavelet ANN (WNN), and Decision Tree (DT) based Software project effort estimation (SPEE) methods.

A New Approach to Calibrating Functional Complexity Weight in Software Development Effort Estimation

Function point analysis is a widely used metric in the software industry for development effort estimation. It was proposed in the 1970s, and then standardized by the International Function Point Users Group, as accepted by many organizations worldwide. While the software industry has grown rapidly, the weight values specified for the standard function point counting have remained the same since its inception. Another problem is that software development in different industry sectors is peculiar, but basic rules apply to all. These raise important questions about the validity of weight values in practical applications. In this study, we propose an algorithm for calibrating the standardized functional complexity weights, aiming to estimate a more accurate software size that fits specific software applications, reflects software industry trends, and improves the effort estimation of software projects. The results show that the proposed algorithms improve effort estimation accuracy against the baseline method.

Hybrid PSO-SA approach for feature weighting in analogy-based software project effort estimation

Software effort estimation plays an important role in software project management, and analogy-based estimation (ABE) is the most common method used for this purpose. ABE estimates the effort required for a new software project based on its similarity to previous projects. A similarity between the projects is evaluated based on a set of project features, each of which has a particular effect on the degree of similarity between projects and the effort feature. The present study examines the hybrid PSO-SA approach for feature weighting in analogy-based software project effort estimation. The proposed approach was implemented and tested on two well-known datasets of software projects. The performance of the proposed model was compared with other optimization algorithms based on MMRE, MDMRE, and PRED(0.25) measures. The results showed that weighted ABE models provide more accurate and better effort estimates relative to unweighted ABE models and that the PSO-SA hybrid approach has led to better and more accurate results compared with the other weighting approaches in both datasets.

Optimization of software cost estimation model based on biogeography-based optimization algorithm

Estimation of software cost (ESC) is considered a crucial task in the software management life cycle as well as time and quality. Prior to the development of a software project, precise estimations are required in the form of person month and time. In the last few decades, various parametric and non-algorithmic or non-parametric approaches regarding the estimation of software costs have been developed. Among them, the constrictive cost model (COCOMO-II) is a commonly used method for estimating software cost. To further improve the accuracy of this model, researchers and practitioners have applied numerous computational intelligence algorithms to optimize their parameters. However, accuracy is still a big problem in this model to be addressed. In this paper, we proposed a biogeography-based optimization (BBO) method to optimize the current coefficients of COCOMO-II for better estimation of software project cost or effort. The experiments are conducted on two standard data sets: NASA-93 and Turkish Industry software projects. The performance of the proposed algorithm called BBO-COCOMO-II is evaluated by using performance indicators including the manhattan distance (MD) and the mean magnitude of relative error (MMRE). Simulation results reveal that the proposed algorithm obtained high accuracy and significant error minimization compared to original COCOMO-II, particle swarm optimization, genetic algorithm, flower pollination algorithm, and other various baseline cost estimation models.

Ensemble Regression Models for Software Development Effort Estimation: A Comparative Study

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.

Regression Based Software Project Effort Estimation with Reusability for Startups

Prediction of effort for software development is the major task for the effective management of any software industry. At present, there are several estimation techniques and tools that are available for a software project. However, choosing the correct and efficient effort prediction of a particular software project is the most demanding task for a start ups. This study focuses on Multiple Linear regression for Software Effort Estimation technique which will provide higher classification accuracy of a software project and thus improves the prediction efficiently. The main aim of the technique is to help developers in startups to classify the project compared to existing software metrics and thereby increasing the software effort prediction rate.

Analogy-Based Approaches to Improve Software Project Effort Estimation Accuracy

Abstract In the discipline of software development, effort estimation renders a pivotal role. For the successful development of the project, an unambiguous estimation is necessitated. But there is the inadequacy of standard methods for estimating an effort which is applicable to all projects. Hence, to procure the best way of estimating the effort becomes an indispensable need of the project manager. Mathematical models are only mediocre in performing accurate estimation. On that account, we opt for analogy-based effort estimation by means of some soft computing techniques which rely on historical effort estimation data of the successfully completed projects to estimate the effort. So in a thorough study to improve the accuracy, models are generated for the clusters of the datasets with the confidence that data within the cluster have similar properties. This paper aims mainly on the analysis of some of the techniques to improve the effort prediction accuracy. Here the research starts with analyzing the correlation coefficient of the selected datasets. Then the process moves through the analysis of classification accuracy, clustering accuracy, mean magnitude of relative error and prediction accuracy based on some machine learning methods. Finally, a bio-inspired firefly algorithm with fuzzy analogy is applied on the datasets to produce good estimation accuracy.

Analogy-based model for software project effort estimation

Accurate effort estimation of software development plays an important role to predict how much effort should be prepared during the works of a software project so that it can be completed on time and budget. Some sectors, e.g. banking sectors, were renowned fields of software projects, not only due to its huge size of project, but also extremely expensive and takes a long time to completion. Project estimation is essential for software development project able to run on time and budget with maximum quality. This study aims to investigate the accuracy of software project effort estimation with the Analogy method using three parameters: Euclidean, Manhattan and Minkowski distance. Analogy based estimation consists several stage included similarity measure, analogy adaptation, estimation calculation and model evaluation. The results showed that the best combination of Analogy methods was using Manhattan distance with an accuracy of 50% MMRE, 28% MdMRE and Pred(25) 48%. Thus, we can concluded that this model can be used to predict accurately.

Application of data mining methods for effort estimation of software projects

SummaryInformation technology companies currently use data mining techniques in different areas with the goal of increasing the quality of decision‐making and to improve their business performance. The study described in this paper uses a data mining approach to produce an effort estimation of a software development process. It is based on data collected in a Croatian information technology company. The study examined 27 software projects with a total effort exceeding 42 000 work hours. The presented model employs a modified Cross‐Industry Standard Process for Data Mining, where prior to model creation, additional clustering of projects is performed. The results generated by the proposed approach generally had a smaller effort estimation error than the results of human experts. The applied approach has proved that sound results can be gained through the use of data mining within the studied area. As a result, it would be wise to use such estimates as additional input in the decision‐making process.

An effective approach for software project effort and duration estimation with machine learning algorithms

During the last two decades, there has been substantial research performed in the field of software estimation using machine learning algorithms that aimed to tackle deficiencies of traditional and parametric estimation techniques, increase project success rates and align with modern development and project management approaches. Nevertheless, mostly due to inconclusive results and vague model building approaches, there are few or none deployments in practice.The purpose of this article is to narrow the gap between up-to-date research results and implementations within organisations by proposing effective and practical machine learning deployment and maintenance approaches by utilization of research findings and industry best practices. This was achieved by applying ISBSG dataset, smart data preparation, an ensemble averaging of three machine learning algorithms (Support Vector Machines, Neural Networks and Generalized Linear Models) and cross validation. The obtained models for effort and duration estimation are intended to provide a decision support tool for organisations that develop or implement software systems.

A CASE Study on Software Project Development Cost, Schedule & Effort Estimation

This paper theme is to provide a case study of Software Project Development cost, effort, and schedule estimation. From recent past, a remarkable research takes place in developing different techniques on software effort and cost estimation. Making estimation before start of any project is necessary to be able to plan and manage any project. The estimate is an intelligent guess for the project resources. Nowadays, software has become a major contributor to economic growth for any nation. Making an estimate before starting any software project is vital for the project managers and key stakeholders. Major project milestones such as project schedules, budgeting, resource allocation, and project delivery dates are set on theeffort and cost estimates. Thus, the reliability of the estimation leads any project success or otherwise fail. In this article, author’s idea is to work with function point analysis and include the concept of workforce scheduling in a better way while taking the decision in the contract phase. That leads to strengthening the relations between the developer and the customer. Basically, size is a main measured unit of the software project. Based on the size and other functionalities, the software managers estimate the total effort required to develop the project. From the effort and work schedule, the total cost can be estimated.

Ontology Based Multiagent Effort Estimation System for Scrum Agile Method

This paper emphasizes on software effort estimation and knowledge management of practicing Scrum methodology that are challenging tasks in agile context. Proposed approach improves software effort estimation and knowledge management of software projects by focusing on Scrum process and practices using ontology model in a multiagent estimation system. It also motivates project key stakeholders to regularly save significant tacit knowledge of unique situations in the form of lessons learnt during the project development. Various agents of the estimation system access the existing knowledge base and autonomously perform their inferencing activities using description logic as per requirements specified by the scrum master and respond with suitable estimate to him/her in the form of time, resources, and lessons learnt for the success of future projects. To validate our approach, an experiment, based on twelve web projects, was conducted using proposed approach, delphi and planning poker estimation methods. The obtained results by applying MMRE, PRED(x) evaluation measures reveals that proposed approach delivers more accurate estimates as compared with delphi and planning poker methods.

Unit effects in software project effort estimation: Work-hours gives lower effort estimates than workdays

Software development effort estimates are typically expert judgment-based and too low to reflect the actual use of effort. Our goal is to understand how the choice of effort unit affects expert judgement-based effort estimates, and to use this knowledge to increase the realism of effort estimates. We conducted two experiments where the software professionals were randomly instructed to estimate the effort of the same projects in work-hours or in workdays. In both experiment, the software professionals estimating in work-hours had much lower estimates (on average 33%–59% lower) than those estimating in workdays. We argue that the unitosity effect—i.e., that we tend to infer information about the quantity from the choice of unit—is the main explanation for the large difference in effort estimates. A practical implication of the unit effect is that, in contexts where there is a tendency toward effort under estimation, the instruction to estimate in higher granularity effort units, such as workdays instead of work-hours, is likely to lead to more realistic effort estimates.

English

Effort estimation is one of the biggest problems faced by software industry. In software planning estimation of the effort is one of the most critical responsibilities. It is necessary to have good effort estimation in order to conduct well budget. The accuracy of the effort estimation of software projects is vital for the competitiveness of software companies. For the forecasting of software effort, it is important to select the correct software effort estimation techniques. Inaccurate effort estimation can be risky to an IT industry’s economics and certainty due to poor quality or trait and stakeholder’s disapproval with the software product. This paper presents M5P decision tree Technique, for effort evaluation in the field of software development

ESTIMATION OF SOFTWARE DEVELOPMENT EFFORT WITH MACHINE LEARNING APPROACHES:A REVIEW

For the initial steps of the software life cycle, it is essential to handle software estimation, because it assists managers bid on projects and allot resources conventionally. In software planning estimation of the effort is one of the most critical responsibilities. It is necessary to have good effort estimation in order to conduct well budget. The accuracy of the effort estimation of software projects is vital for the competitiveness of software companies. For the forecasting of software effort, it is important to select the correct software effort estimation techniques. Inaccurate effort estimation can be risky to an IT industry’s economics and certainty due to poor quality or trait and stakeholder’s disapproval with the software product. This paper presents the most commonly used machine learning techniques such as Multi-Layer Perceptron, linear regression, decision tree, for effort evaluation in the field of software development.

Numerical anchors and their strong effects on software development effort estimates

The anchoring effect may be described as the tendency for an initial piece of information to influence people's subsequent judgement, even when the information is irrelevant. Previous studies suggest that anchoring is an important source of inaccurate software development effort estimates. This article examines how the preciseness and credibility of anchoring information affects effort estimates. Our hypotheses were that anchors with lower numerical precision and anchor sources with lower credibility would have less impact on effort estimates. The results from three software project effort estimation experiments, with 381 software professionals, support previous findings about the relevance of anchoring effects to software effort estimation. However, we found no decrease in the anchoring effect with decreasing anchor precision or source credibility. This suggests that even implausible anchors from low-credibility sources can lead to anchoring effects, and that all kinds of misleading information potentially acting as estimation anchors in project estimation contexts should be avoided.

ROC curves for regression

Receiver Operating Characteristic (ROC) analysis is one of the most popular tools for the visual assessment and understanding of classifier performance. In this paper we present a new representation of regression models in the so-called regression ROC (RROC) space. The basic idea is to represent over-estimation against under-estimation. The curves are just drawn by adjusting a shift, a constant that is added (or subtracted) to the predictions, and plays a similar role as a threshold in classification. From here, we develop the notions of optimal operating condition, convexity, dominance, and explore several evaluation metrics that can be shown graphically, such as the area over the RROC curve (AOC). In particular, we show a novel and significant result: the AOC is equivalent to the error variance. We illustrate the application of RROC curves to resource estimation, namely the estimation of software project effort.