Advanced effort estimation in software projects using ensemble-based fusion techniques

An international association advancing the multidisciplinary study of informing systems. Founded in 1998, the Informing Science Institute (ISI) is a global community of academics shaping the future of informing science.

Software project effort estimation is a major process in software development cycle. This process helps in decision making in resource allocation and distribution. In this work, a new effort estimation clustering method based on estimation maximization soft-clustering unsupervised machine learning algorithm is proposed. This model classifies any software project into one of four categories. An enterprise will accept to develop a software project if this project is clustered into a class that requires resources equal or less than the enterprises resources. The new model helps in decision making process in one hand and helps consumers in assigning projects to a developing enterprise in the other hand. COCOMO dataset has been used to implement, deploy and test the model. The propose model has been compared with K-means algorithm to show the differences between soft and hard clustering. The paper results show that soft-clustering has the ability to estimate efforts like any supervised machine learning algorithms.

Objective. The objective of this paper is to provide a framework for effort management in software projects to increase effort estimation accuracy. Method. We applied a multimethodological approach employing a case study and constructive research. Results. Based on the case study on four earlier proposed frameworks related to effort management and three popular process maturity assessment models, we constructed a framework to manage effort in a software project in a proactive manner, yet fulfilling the requirements of the assessment models. Conclusions. A project’s software engineering process involves various functions which have an effect on the success of effort estimation. Two approaches, proactive and reactive, can be taken to manage effort in a software project. In this paper, a case study is conducted regarding both approaches. Based on the case study, we provide a new framework for effort management in software projects to increase effort estimation accuracy.

The estimation of software development effort has been centralized mostly on the accuracy of estimates through dealing with heterogeneous datasets regardless of the fact that the software projects are inherently complex and uncertain. In particular, Analogy Based Estimation (ABE), as a widely accepted estimation method, suffers a great deal from the problem of inconsistent and non-normal datasets because it is a comparison-based method and the quality of comparisons strongly depends on the consistency of projects. In order to overcome this problem, prior studies have suggested the use of weighting methods, outlier elimination techniques and various types of soft computing methods. However the proposed methods have reduced the complexity and uncertainty of projects, the results are not still convincing and the methods are limited to a special domain of software projects, which causes the generalization of methods to be impossible. Localization of comparison and weighting processes through clustering of projects is the main idea behind this paper. A hybrid model is proposed in which the software projects are divided into several clusters based on key attributes (development type, organization type and development platform). A combination of ABE and Particle Swarm Optimization (PSO) algorithm is used to design a weighting system in which the project attributes of different clusters are given different weights. Instead of comparing a new project with all the historical projects, it is only compared with the projects located in the related clusters based on the common attributes. The proposed method was evaluated through three real datasets that include a total of 505 software projects. The performance of the proposed model was compared with other well-known estimation methods and the promising results showed that the proposed localization can considerably improve the accuracy of estimates. Besides the increase in accuracy, the results also certified that the proposed method is flexible enough to be used in a wide range of software projects.

The effort involved in developing a software product plays an important role in determining the success or failure. In the context of developing software using object oriented methodologies, traditional methods and metrics were extended to help managers in effort estimation activity. Software project managers require a reliable approach for effort estimation. It is especially important during the early stage of the software development life cycle. In this paper, the main goal is to estimate the cost of various software projects using class point approach and optimize the parameters using six types of adaptive regression techniques such as multi-layer perceptron, multivariate adaptive regression splines, projection pursuit regression, constrained topological mapping, K nearest neighbor regression and radial basis function network to achieve better accuracy. Also a comparative analysis of software effort estimation using these various adaptive regression techniques has been provided. By estimating the effort required to develop software projects accurately, we can have softwares with acceptable quality within budget and on planned schedules.

Software projects typically require effort estimation from the software development life cycle (SDLC) staff at the commencement of the software development activities. Inaccuracies in effort estimation of software projects early on in the SDLC continues to be a perennial problem. Typically, improved estimates for software projects are provided under circumstances where requirements engineering (RE) is completed. RE provides a key reference in the form of requirements for the estimation process. However, RE by itself may consume significant effort demanding the RE phase to be estimated as the first step in the SDLC. It is difficult to establish RE estimates, as RE usually has no tangible reference on which estimates can be based. This paper provides a practical estimation method for large and complex RE processes. We demonstrate using a case study snapshot in a large software organization that the method provides improved effort estimates for the RE process.

Effort estimation is still one of the most daunting, hard to apply tasks in any given software project. Although many current methodologies propose an incremental approach to software development, there are still few techniques that allow them to be applied efficiently. We developed TUPUX, an add-in component for StarUML that facilitates the planning and estimation, using Function Points, in software projects that adopt the incremental model. The technique supported by our tool has been tested in several undergraduate-level software development projects, yielding promising results. Additionally, our software supports use-case specification as a previous activity to effort estimation. It also employs analysis class diagrams to facilitate a semi-automated Function Point counting process to be applied.

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.

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.

Accurate software effort estimation is one of the key factors to a successful project by making a better software project plan. To improve the estimation accuracy of software effort, many studies usually aimed at proposing novel effort estimation methods or combining several approaches of the existing effort estimation methods. However, those researches did not consider the distribution of historical software project data which is an important part impacting to the effort estimation accuracy. In this paper, to improve effort estimation accuracy by least squares regression, we propose a data partitioning method by the accuracy measures, MRE and MER which are usually used to measure the effort estimation accuracy. Furthermore, the empirical experimentations are performed by using two industry data sets (the ISBSG Release 9 and the Bank data set which consists of the project data performed in a bank in Korea).

One of the pillars for sound Software Project Management is reliable effort estimation. Therefore it is important to fully identify what are the fundamental factors that affect an effort estimate for a new project and how these factors are inter-related. This paper describes a case study where a Bayesian Network model to estimate effort for healthcare software projects was built. This model was solely elicited from expert knowledge, with the participation of seven project managers, and was validated using data from 22 past finished projects. The model led to numerous changes in process and also in business. The company adapted their existing effort estimation process to be in line with the model that was created, and the use of a mathematically-based model also led to an increase in the number of projects being delegated to this company by other company branches worldwide.

A project effort estimation study

Effort estimation models have been long studied in software engineering research. Effort estimation models help organizations and individuals plan and track progress of their software projects and individual tasks to help plan delivery milestones better. Towards this end, there is a large body of work that has been done on effort estimation for projects but little work on an individual checkin (Pull Request) level. In this paper we present a methodology that provides effort estimates on individual developer check-ins which is displayed to developers to help them track their work items. Given the cloud development infrastructure pervasive in companies, it has enabled us to deploy our Pull Request Lifetime prediction system to several thousand developers across multiple software families. We observe from our deployment that the pull request lifetime prediction system conservatively helps save 44.61% of the developer time by accelerating Pull Requests to completion.

A software development project can be considered to be risky project due to the uncertainty of the information (customer requirements), the complexity of the process, and the intangible nature of the product. Under these conditions, risk management in software development projects is mandatory, but often it is difficult and expensive to implement. Expert COCOMO is an efficient approach to software project risk management, which leverages existing knowledge and expertise from previous effort estimation activities to assess the risk in a new software project. However, the original method has a limitation because it cannot effectively deal with imprecise and uncertain inputs in the form of linguistic terms such as: Very Low (VL), Low (L), Nominal (N), High (H), Very High (VH) and Extra High (XH). This paper introduces the fuzzy-ExCOM methodology that combines the advantages of a fuzzy technique with Expert COCOMO methodology for risk assessment in a software project. A validation of this approach with project data shows that fuzzy-ExCOM provides better risk assessment results with a higher level of sensitivity with respect to risk identification compared to the original Expert COCOMO methodology.

Software effort estimation (SEE) is an important process for predicting the effort required to develop or maintain software projects. It is considered one of the difficult challenges for software engineering because the more accurate the estimation, the greater the chances of success in developing software projects to complete and deliver them within the specified scheduling and budget. The diversity in software projects led to the use of many techniques to estimate the effort. The main objective of the research is to find the best technique to get the estimated effort as close to the real effort, using Machine learning Algorithms, artificial neural network Long Short-Term Memory(LSTM) and the artificial neural network Stacked Long Short-Term Memory (Stacked_LSTM), with six data sets are China, Kitchenham, Kemerer, Cocomo 81, Albrecht, Decharnais, and comparing the performance of the two machine learning algorithms performance, Neuralnet and Lasso from previous research, used the same data sets and using the same evaluation metrics, which are: the root mean square error (RMSE), mean absolute error (MAE) and R_Squared. The results demonstrated the superiority of the Stacked _LSTM algorithm by all metrics with the dataset of China, Kemerer and Albrecht, while in the data sets, Descharnais and Kitchenham, the LSTM algorithm outperformed the rest of the methods. While in the Cocomo 81 dataset, Neuralnet algorithm outperformed the rest of the techniques used, but the best rating was obtained. It is for Stacked _LSTM algorithm with China data.