Analogy-based Estimation Research Articles

Using Standard Deviation with Analogy-Based Estimation for Improved Software Effort Prediction

Using Standard Deviation with Analogy-Based Estimation for Improved Software Effort Prediction

An Intelligent Framework for Estimating Software Development Projects using Machine Learning

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.

Agile Software Development Effort Estimation based on Product Backlog Items

In all methods of Agile Software Development methods, an estimation process which determines the size of all Product Backlog Items (PBI) is essentially important. One of those methods is Planning Poker. This method is familiar among developers in the globe and one of the famous analogy-based estimation techniques known. In Planning Poker, the goal is to have a consensus vote on how big a product backlog should be. This consensus is reached via open discussion. As discussion is involved, many aspects of human errors could cause problems such as: anchoring effect and overconfidence which often leads to underestimation. To comprehend this, we offer an AI method that can be applied alongside the discussion to minimize this human error factors. We will be using NLP and ANN to classify a Product Backlog Item based on previous projects. The aim is individual estimate given by the AI that is free from influence from human to give better estimation. The result is expected at above 90% accuracy to give the best performance.

Stacking regularization in analogy-based software effort estimation.

Analogy-based estimation (ABE) estimates the effort of the current project based on the information of similar past projects. The solution function of ABE provides the final effort prediction of a new project. Many studies on ABE in the past have provided various solution functions, but its effectiveness can still be enhanced. The present study is an attempt to improve the effort prediction accuracy of ABE by proposing a solution function SABE: Stacking regularization in analogy-based software effort estimation. The core of SABE is stacking, which is a machine learning technique. Stacking is beneficial as it works on multiple models harnessing their capabilities and provides a better estimation accuracy as compared to a single model. The proposed method is validated on four software effort estimation datasets and compared with the already existing solution functions: closet analogy, mean, median and inverse distance weighted mean. The evaluation criteria used are mean magnitude of relative error (MMRE), median magnitude of relative error (MdMRE), prediction (PRED) and standard accuracy (SA). The results suggested that the SABE showed promising performance for almost all the evaluation criteria when compared with the results of the earlier studies.

Polynomial analogy‐based software development effort estimation using combined particle swarm optimization and simulated annealing

SummarySoftware development effort estimation is an effective factor in the success or failure of software projects. There are several methods to estimate the effort of software projects, the most common of which is analogy‐based estimation (ABE). In this article, a polynomial version of ABE (named PABE) is presented, in which, the project effort is calculated based on a polynomial ensemble of different ABE models. To optimize the controllable parameters of the PABE model, a combined global–local search metaheuristic algorithm based on particle swarm optimization and simulated annealing is utilized in two steps. At the first step, for each similarity and adaptation function, the optimized ABE model is determined by exploiting the optimal value of feature weights, the number of similar projects, and other parameters of the ABE model. Then, at the second step, the amount of effort attained by the optimized models is used for estimating the final effort by the proposed polynomial equation. The proposed PABE method has been successfully executed on five well‐known software effort estimation datasets: Maxwell, Albrecht, Cocomo81, Desharnais, and Kemerer. Obtained results show the superiority of the proposed PABE model in terms of accuracy and efficiency compared to other techniques.

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.

A Generic Analogy-Centered Software Cost Estimation Based on Differential Evolution Exploration Process

Abstract Software cost estimation is the prediction of development effort and calendar time required to develop any software project. It is considered to be the very fundamental task for successful execution of an on-going project as well as budgetary requirements of futuristic projects. As accuracy in software cost estimation is very hard because of the availability of vague information at the time of inception of the software project, it prompted many researchers to explore in this domain from past decades. Their pioneer works suggest a bulk of techniques for this purpose. However, because of the availability of large number of estimation techniques, it becomes hard for any software practitioners to select an appropriate one. To help the industry practitioners in these situations, a novel analogy-centered model based on differential evolution exploration process is proposed in this research study. The proposed model has been assessed on 676 projects from 5 different data sets and the results achieved are significantly better when compared with other benchmark analogy-based estimation studies. Furthermore, being the very less computational cost of the proposed model, it is suggested that the proposed model be considered as the preliminary stage of any analogy-based software estimation technique.

Fuzzy C-mean Missing Data Imputation for Analogy-based Effort Estimation

The accuracy of effort estimation in one of the major factors in the success or failure of software projects. Analogy-Based Estimation (ABE) is a widely accepted estimation model since its flow human nature in selecting analogies similar in nature to the target project. The accuracy of prediction in ABE model in strongly associated with the quality of the dataset since it depends on previous completed projects for estimation. Missing Data (MD) is one of major challenges in software engineering datasets. Several missing data imputation techniques have been investigated by researchers in ABE model. Identification of the most similar donor values from the completed software projects dataset for imputation is a challenging issue in existing missing data techniques adopted for ABE model. In this study, Fuzzy C-Mean Imputation (FCMI), Mean Imputation (MI) and K-Nearest Neighbor Imputation (KNNI) are investigated to impute missing values in Desharnais dataset under different missing data percentages (Desh-Miss1, Desh-Miss2) for ABE model. FCMI-ABE technique is proposed in this study. Evaluation comparison among MI, KNNI, and (ABE-FCMI) is conducted for ABE model to identify the suitable MD imputation method. The results suggest that the use of (ABE-FCMI), rather than MI and KNNI, imputes more reliable values to incomplete software projects in the missing datasets. It was also found that the proposed imputation method significantly improves software development effort prediction of ABE model.

Ensembling Artificial Bee Colony With Analogy-Based Estimation to Improve Software Development Effort Prediction

Analogy-Based Estimation (ABE) is one of the promising estimation models used for predicting the software development effort. Researchers proposed different variants of the ABE model, but still, the most suitable procedure could not be produced for accurate estimation. In this study, an artificial Bee colony guided Analogy-Based Estimation (BABE) model is proposed which ensembles Artificial Bee Colony (ABC) with ABE for accurate estimation. ABC produces different weights, out of which the most appropriate is infused in the similarity function of ABE during the stage of model training, which are later used in the testing stage for evaluation. There are six real datasets utilized for simulating the model procedure. Five of these datasets are taken from the PROMISE repository. The predictive performance is improved for BABE over the existing ones. The most significant of its performance is found on the International Software Benchmarking Standards Group (ISBSG) dataset.

MINN: A Missing Data Imputation Technique for Analogy-based Effort Estimation

Success and failure of a complex software project are strongly associated with the accurate estimation of development effort. There are numerous estimation models developed but the most widely used among those is Analogy-Based Estimation (ABE). ABE model follows human nature as it estimates the future project’s effort by making analogies with the past project's data. Since ABE relies on the historical datasets, the quality of the datasets affects the accuracy of estimation. Most of the software engineering datasets have missing values. The researchers either delete the projects containing missing values or avoid treating the missing values which reduce the ABE performance. In this study, Numeric Cleansing (NC), K-Nearest Neighbor Imputation (KNNI) and Median Imputation of the Nearest Neighbor (MINN) methods are used to impute the missing values in Desharnais and DesMiss datasets for ABE. MINN technique is introduced in this study. A comparison among these imputation methods is performed to identify the suitable missing data imputation method for ABE. The results suggested that MINN imputes more realistic values in the missing datasets as compared to values imputed through NC and KNNI. It was also found that the imputation treatment method helped in better prediction of the software development effort on ABE model.

Combining Data Analytics with Team Feedback to Improve the Estimation Process in Agile Software Development

Abstract We apply a mixed research method to improve the user stories estimation process in a German company following agile software development. We combine software project data analytics with elicitation of teams’ feedback, identify root causes for wrong estimates and propose an improved version of the estimation process. Three major changes are adopted in the new process: a shorter non numerical scale for story points, an analogy-based estimation process, and retrospectives analyses on the accuracy of previous sprints estimates. The new estimation process is applied on a new project, and an improvement of estimates accuracy from 10% to 45% is observed.

DABE: Differential evolution in analogy-based software development effort estimation

Abstract Several feature weight optimization techniques have been proposed for similarity functions in analogy-based estimation (ABE); however, no consensus regarding the method and settings suitable for producing accurate estimates has been reached. We investigate the effectiveness of differential evolution (DE) algorithm, for optimizing the feature weights of similarity functions of ABE by applying five successful mutation strategies. We have named this empirical analysis as DE in analogy-based software development effort estimation (DABE). We have conducted extensive simulation study on the PROMISE repository test suite to estimate the effectiveness of our proposed DABE technique. We find significant improvements in predictive performance of our DABE technique over ABE, particle swarm optimization-based feature weight optimization in ABE, genetic algorithm-based feature weight optimization in ABE, self-adaptive DE-based feature weight optimization ABE, adaptive differential evolution with optional external archive-based feature weight optimization ABE, functional link artificial neural network,artificial neural network with back propagation learning based software development effort estimation (SDEE), and radial basis function-based SDEE.

A differential evolution-based model to estimate the software services development effort

Accurate estimation of software service development effort is a great challenge both in industry and for academia. The concept of effort is an important and effective parameter in process development and software service management. The reliable estimation of effort helps the project managers to allocate the resources better and manage cost and time so that the project will be finished in the determined time and budget. One of the most popular effort estimation methods is analogy-based estimation ABE to compare a service with similar historical cases. Unfortunately, ABE is not capable of generating accurate results unless determining weights for service features. Therefore, this paper aims to make an efficient and reliable model through combining ABE method and differential evolution algorithm to estimate the software services development effort. In fact, the differential evolution algorithm was utilized for weighing features in the similarity function of the ABE method. This weighing process could help determining the importance level of the various service features and extracting the best similar historical case. The proposed hybrid model has been evaluated on two real datasets and two artificial datasets. The obtained results were compared with common effort estimation methods. This comparison showed more accuracy, faster convergence, and lower cost of the proposed model. Copyright © 2015 John Wiley & Sons, Ltd.

Pareto efficient multi-objective optimization for local tuning of analogy-based estimation

Analogy-based effort estimation (ABE) is one of the prominent methods for software effort estimation. The fundamental concept of ABE is closer to the mentality of expert estimation but with an automated procedure in which the final estimate is generated by reusing similar historical projects. The main key issue when using ABE is how to adapt the effort of the retrieved nearest neighbors. The adaptation process is an essential part of ABE to generate more successful accurate estimation based on tuning the selected raw solutions, using some adaptation strategy. In this study, we show that there are three interrelated decision variables that have great impact on the success of adaptation method: (1) number of nearest analogies (k), (2) optimum feature set needed for adaptation and (3) adaptation weights. To find the right decision regarding these variables, one need to study all possible combinations and evaluate them individually to select the one that can improve all prediction evaluation measures. The existing evaluation measures usually behave differently, presenting sometimes opposite trends in evaluating prediction methods. This means that changing one decision variable could improve one evaluation measure while it is decreasing the others. Therefore, the main theme of this research is how to come up with best decision variables that improve adaptation strategy and thus the overall evaluation measures without degrading the others. The impact of these decisions together has not been investigated before; therefore, we propose to view the building of adaptation procedure as a multi-objective optimization problem. The Particle swarm optimization algorithm (PSO) is utilized to find the optimum solutions for such decision variables based on optimizing multiple evaluation measures. We evaluated the proposed approaches over 15 datasets and using four evaluation measures. After extensive experimentation, we found that: (1) predictive performance of ABE has noticeably been improved, (2) optimizing all decision variables together is more efficient than ignoring any one of them, and (3) optimizing decision variables for each project individually yields better accuracy than optimizing them for the whole dataset.

Accuracy Comparison of Analogy-Based Software Development Effort Estimation Techniques

Estimation by analogy is a commonly used software effort estimation technique and a suitable alternative to other conventional estimation techniques: It predicts the effort of the target project using information from former similar projects. While it is relatively easy to handle numerical attributes, dealing with categorical attributes is one of the most difficult issues for analogy-based estimation techniques. Therefore, we propose, in this paper, a novel analogy-based approach, called 2FA-kprototypes, to predict effort when software projects are described by a mix of numerical and categorical attributes. To this aim, the well-known fuzzy k-prototypes algorithm is integrated into the process of estimation by analogy. The estimation accuracy of 2FA-kprototypes was evaluated and compared with that of two techniques: 1 classical analogy-based technique and 2 2FA-kmodes, which is a technique that we have developed recently. The comparison was performed using four data sets that are quite diverse and have different sizes: ISBSG, COCOMO, USP05-FT, and USP05-RQ. The results obtained showed that both 2FA-kprototypes and 2FA-kmodes perform better than classical analogy.

Model to estimate the software development effort based on in‐depth analysis of project attributes

Over the past years, numerous models have been proposed to estimate the development effort in the early stages of a software project. The existing models have mostly relied on soft computing techniques and weighting methods. Although they have reduced the complexity and vagueness of software project attributes, attempts are ongoing to develop more accurate and reliable estimation models. This paper is concentrated on selective classification of software projects based on underlying attributes to localise the development effort estimation process in a widely used model called analogy-based estimation (ABE). The proposed model is a combination of ABE, selective classification and a weighting system in which the attributes of different software projects are assigned different weights. In fact, the process of attribute weighting is customised based on the nature of project being estimated. A real data set was utilised to evaluate the performance of the proposed model. A comparison between the estimates achieved by the proposed model and those obtained from other well-known effort estimation models showed that the proposed model substantially improves the performance metrics. Along with the improvement of accuracy, the proposed model is able to be used in an extensive domain of software projects.

Insightful analogy-based software development effort estimation through selective classification and localization

Accurate development effort estimation is a challenging issue in the management of software projects because it can considerably affect the planning and scheduling of a software project. Over the past few years, many algorithmic and non-algorithmic methods have been proposed to estimate the development effort in the early stages of project. Due to simplicity and estimation capability, analogy-based estimation (ABE) method has been widely accepted by researchers in this area. In spite of the fact that ABE is an efficient estimation method, it suffers from the non-normality and heterogeneous nature of software project datasets. Although prior studies have strived to remedy this issue by weighting, soft computing, and clustering techniques, the estimate accuracy is still not convincing and attempts are ongoing to reach more reliable estimates. The problem is that prior ABE-based studies have not considered the nature of software projects in the estimation process. This paper aims to show the effect of selective project classification and estimation process localization on the performance of ABE. An exhaustive investigation is conducted based on different development types, organization types, and development platforms as three underlying attributes in software projects. An evaluation framework is designed to reveal the ABE performance when it is combined with the proposed classification. A real dataset that includes 448 software projects is utilized for the evaluation purposes. The promising results showed that the estimate accuracy is significantly improved and the estimation process is considerably expedited if the nature of software projects is considered in the ABE method.

Towards Improvement of Analogy-Based Software Development Effort Estimation: A Review

In this paper a systematic review is conducted to investigate the structure, components, techniques, evaluation procedure, and comparison scope related to prior ABE-based studies. The undeniable role of accurate development effort estimation in the success of software project management has attracted the attention of researchers over the past few years. Among various algorithmic and non-algorithmic estimation methods, analogy based estimation (ABE) is a widely accepted method due to its simplicity and estimation capability. This paper investigates the improvement process of ABE method during 2000 to 2012. Six research questions are defined to be addressed through evaluation of prior ABE-based studies. The review domain includes 24 papers selected through a tough filtration process. The results show that improvement of ABE can be performed through adjustment, grey theory, attribute weighting and attribute selection techniques. Moreover, ABE configurations can significantly affect the results.

Effects of Product Attributes in Case-Based Reasoning Methods for Cost Estimation and Cost Uncertainty Modeling

This paper presents case-based reasoning methods for cost estimation and cost uncertainty modeling that may help designers select a new product concept at the early stage of product development. The case-based reasoning methods without cost adjustment (CBR) and with cost adjustment (CBR-A) are compared with analogy-based cost estimation (ABCE) and multivariate linear regression analysis (RA). Under the conditions studied in the illustrative example of this paper (i.e., a single knowledge base, sport utility vehicle (SUV) concepts, and up to five concept attributes), leave-one-out cross-validation results indicate that both CBR-A and RA accurately estimate cost and reliably model cost uncertainty; and optimum attribute sets for the most accurate cost estimation and the most reliable cost uncertainty modeling are different in all methods. The results of this paper indicate that designers may need to carefully select attribute sets by analyzing trade-offs between the accuracy of cost estimation and the reliability of cost uncertainty modeling when product cost is used as a criterion to select concepts.

An Optimized Analogy-Based Project Effort Estimation

despite the predictive performance of Analogy-Based Estimation (ABE) in generating better effort estimates, there is no consensus on: (1) how to predetermine the appropriate number of analogies, (2) which adjustment technique produces better estimates. Yet, there is no prior works attempted to optimize both number of analogies and feature distance weights for each test project. Perhaps rather than using fixed number, it is better to optimize this value for each project individually and then adjust the retrieved analogies by optimizing and approximating complex relationships between features and reflects that approximation on the final estimate. The Artificial Bees Algorithm is utilized to find, for each test project, the appropriate number of closest projects and features distance weights that is used to adjust those analogies’ efforts. The proposed technique has been applied and validated to 8 publically datasets from PROMISE repository. Results obtained show that: (1) the predictive performance of ABE has noticeably been improved, (2) the number of analogies was remarkably variable for each test project. While there are many techniques to adjust ABE, Using optimization algorithm provides two solutions in one technique and appeared useful for datasets with complex structure.