Cluster-based fuzzy regression trees for software cost prediction

IFIP International Federation for Information Processing, 2006

This paper suggests several estimation guidelines for the choice of a suitable machine learning technique for software development effort estimation. Initially, the paper presents a review of relevant published studies, pointing out pros and cons of specific machine learning methods. The techniques considered are Association Rules, Classification and Regression Trees, Bayesian Belief Networks, Neural Networks and Clustering, and they are compared in terms of accuracy, comprehensibility, applicability, causality and sensitivity. Finally the study proposes guidelines for choosing the appropriate technique, based on the size of the training data and the desirable features of the extracted estimation model.

Journal of Systems and Software, 2008

Parametric software cost estimation models are based on mathematical relations, obtained from the study of historical software projects databases, that intend to be useful to estimate the effort and time required to develop a software product. Those databases often integrate data coming from projects of a heterogeneous nature. This entails that it is difficult to obtain a reasonably reliable single parametric model for the range of diverging project sizes and characteristics. A solution proposed elsewhere for that problem was the use of segmented ...

World Applied Sciences …, 2011

Project planning plays a significant role in software projects so that imprecise estimations often lead to the project faults or dramatic outcomes for the project team. In recent years, various methods have been proposed to estimate the software development effort accurately. Among all proposed methods the non algorithmic methods by using soft computing techniques have presented considerable results. Complexity and uncertain behavior of software projects are the main reasons for going toward the soft computing techniques. In this paper a hybrid system based on combining C-Means clustering, neural network and analogy method is proposed. Since, there are complicated and non linear relations among software project features, the proposed method can be useful to interpret such relations and to present more accurate estimations. The obtained results showed that fuzzy clustering could decrease the negative effect of irrelevant projects on accuracy of estimations. In addition, evaluation of proposed hybrid method showed the significant improvement of accuracy as compared to the neural network the analogy method and statistical methods.

2020

Software cost prediction is the technique of accurately evaluating the amount while developing the software. Estimation involves the total time required for the completion of the software, effort required that is measured in terms of person per month (PM), and the total cost to complete the activity. Accuracy and duration are the two desirable criteria in the software estimation process. In software estimation process, there are several inputs that are being fed to the system and these inputs are used for the generation or calculation of the set of outputs. The important work of the software project managers in the present scenario is the computation of cost or effort before the absolute advancement of any particular software. There are several methods applied for software cost estimation but we will focus on the fuzzy logic which is a soft-computing method. We feel that model which is based on fuzzy logic for the software cost estimation should be able to give the uncertain values ...

2015

Software cost estimation is the process of predicting the effort required to develop a software system. Many estimation models have been proposed over the last 30 years. With the development of software engineering, estimation of project cost and duration has been a very important work. It plays an important role in project bid and project planning. Many papers have been published regarding this topic, which aims at predicting costs of projects to a tolerable degree of accuracy at the early stage. In this paper, several existing fuzzy logic methods for software cost estimation are illustrated and they are compared with the intermediate COCOMO model. Comparing the features of the methods, it could be applied for clustering based on abilities and is also useful for selecting the special method for each project.

The correct cost estimation for software companies and company executives and companies is very important task. In required effort prediction, estimated time of delivery and cost of the project with high accuracy is still vast challenge for projects masters. For many years, algorithmic models like Constructive Cost Model (COCOMO) families were used for required effort prediction. Nowadays, intelligent methods have many applications in SCE. In this study, we firstly give introduction to software cost estimation (SCE) and requirements. Then, we proposed a new intelligent approach by means of additive regression model for classifying the training and testing instances on NASA projects. The results show that our proposed system is more effective. Performance is evaluated by comparing the COCOMO and additive regression based classifier results.

International Journal of Advanced Computer Science and Applications, 2011

Web Effort Estimation is a process of predicting the efforts and cost in terms of money, schedule and staff for any software project system. Many estimation models have been proposed over the last three decades and it is believed that it is a must for the purpose of: Budgeting, risk analysis, project planning and control, and project improvement investment analysis. In this paper, we investigate the use of Fuzzy ID3 decision tree for software cost estimation, it is designed by integrating the principles of ID3 decision tree and the fuzzy settheoretic concepts, enabling the model to handle uncertain and imprecise data when describing the software projects, which can improve greatly the accuracy of obtained estimates. MMRE and Pred are used, as measures of prediction accuracy, for this study. A series of experiments is reported using Tukutuku software projects dataset. The results are compared with those produced by three crisp versions of decision trees: ID3, C4.5 and CART.

A tool named 2CEE was developed for developing new software cost estimation model using data mining technique. The accuracy of these models has been validated internally through N-Fold Cross Validation (also called Leave One Out Cross Validation. However these newly developed models are well predicted and validated in the real world through various researches. This paper is going to find out how well this machine learning algorithm such as Naive Bayes classification and neural network can be applied for cost estimation using COCOMO II cost model for comparisons. This estimate the new project with comparing the past project data or cost driver in past project data with the help of data mining tool Weka.

2010

A new software cost estimation approach is proposed in this paper, which attempts to cluster empirical, non-homogenous project data samples via an entropy-based fuzzy k-modes clustering algorithm. The target is to identify groups of projects sharing similar characteristics in terms of cost attributes or descriptors, and utilise this grouping information to provide estimations of the effort needed for a new project that is classified in a certain group. The effort estimates produced address the uncertainty and fuzziness of the clustering process by yielding interval predictions based on the mean and standard deviation of the samples having strong membership within a cluster. Empirical validation of the proposed methodology was conducted using a filtered version of the ISBSG dataset and yielded encouraging results both in terms of practical usage of the clustered groups and of approximating effectively project costs.

One of the challenges faced by the managers in the software industry today is the ability to accurately define the requirements of the software projects early in the software development phase. The cost-benefit analysis forms the basis of the planning and decision making throughout the software development lifecycle. As such there is a need for efficient software cost estimation techniques for making any endeavor viable. Software cost estimation is the process of prognosticating the amount of effort required to build a software project. In this paper we have proposed a Particle Swarm Optimization (PSO) technique which operates on data sets clustered using the K-means clustering algorithm. PSO is employed to generate parameters of the COCOMO model for each cluster of data values. The clusters and effort parameters are then trained to a Neural Network by using Back propagation technique, for classification of data. Here we have tested the model on the COCOMO 81 dataset and also compared the obtained values with standard COCOMO model. By making use of the experience from Neural Networks and the efficient tuning of parameters by PSO operating on clusters, the proposed model is able to generate better results and it can be applied efficiently to larger data sets.

2011

Web Effort Estimation is a process of predicting the efforts and cost in terms of money, schedule and staff for any software project system. Many estimation models have been proposed over the last three decades and it is believed that it is a must for the purpose of: Budgeting, risk analysis, project planning and control, and project improvement investment analysis. In this paper, we investigate the use of Fuzzy ID3 decision tree for software cost estimation; it is designed by integrating the principles of ID3 decision tree and the fuzzy set-theoretic concepts, enabling the model to handle uncertain and imprecise data when describing the software projects, which can improve greatly the accuracy of obtained estimates. MMRE and Pred are used as measures of prediction accuracy for this study. A series of experiments is reported using two different software projects datasets namely, Tukutuku and COCOMO’81 datasets. The results are compared with those produced by the crisp version of the...

JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer), 2021

Software development involves several interrelated factors that influence development efforts and productivity. Improving the estimation techniques available to project managers will facilitate more effective time and budget control in software development. Software Effort Estimation or software cost/effort estimation can help a software development company to overcome difficulties experienced in estimating software development efforts. This study aims to compare the Machine Learning method of Linear Regression (LR), Multilayer Perceptron (MLP), Radial Basis Function (RBF), and Decision Tree Random Forest (DTRF) to calculate estimated cost/effort software. Then these five approaches will be tested on a dataset of software development projects as many as 10 dataset projects. So that it can produce new knowledge about what machine learning and non-machine learning methods are the most accurate for estimating software business. As well as knowing between the selection between using Par...

2013

Accurate software development effort estimation is critical to the success of software projects. Although many techniques and algorithmic models have been developed and implemented by practitioners, accurate software development effort prediction is still a challenging endeavor in the field of software engineering, especially in handling uncertain and imprecise inputs and collinear characteristics. In this paper, a hybrid in-telligent model combining a neural network model integrated with fuzzy model (neuro-fuzzy model) has been used to improve the accuracy of estimating software cost. The performance of the proposed model is assessed by designing and conducting evaluation with published project and industrial data. Results have shown that the proposed model demonstrates the ability of improving the estimation accuracy by 18% based on the Mean Magnitude of Relative Error (MMRE) criterion.

Procedia Technology, 2012

Software Cost Estimation (SCE) is one of important topics in producing software in recent decades. Real estimation requires cost and effort factors in producing software by using of algorithmic or Artificial Intelligent (AI) techniques. Boehm developed the Constructive Cost Model (COCOMO) that is one of the algorithmic SCE models. Also, these models contain three increasingly basic, intermediate and detailed forms, i.e. basic COCOMO is suitable for quick, early, rough order of among the estimates of required effort in producing software, but its accuracy is limited due to its loss of factors to account for difference between cost drivers. Intermediate COCOMO assumes these project attributes into account. In addition detailed COCOMO accounts for individual project phases used. The COCOMO algorithmic techniques families have used since 1981. In recent years, some techniques emerged by using intelligent techniques to solve and estimate the effort required in producing software. In this paper, different data mining techniques to estimate software costs are presented and then the results of each technique are evaluated and compared. However, NASA's projects to train and test each of these techniques are applied. Then, data set to train and test the data mining techniques improve the estimation accuracy of the models in many cases. We show the comparison between COCOMO model and data mining techniques here. The results indicate that these methods result in many benefit answers. Also we show the comparison of the estimation accuracy of COCOMO model with data mining techniques. Data mining techniques improve the estimation accuracy of the models in many cases. So the estimated effort more improvement in this models.

Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 2011

This empirical study investigates two commonly used decision tree classification algorithms in the context of cost-sensitive learning. A review of the literature shows that the cost-based performance of a software quality prediction model is usually determined after the model-training process has been completed. In contrast, we incorporate cost-sensitive learning during the model-training process. The C4.5 and Random Forest decision tree algorithms are used to build defect predictors either with, or without, any cost-sensitive learning technique. The paper investigates six different cost-sensitive learning techniques: AdaCost, Adc2, Csb2, MetaCost, Weighting, and Random Undersampling (RUS). The data come from case study include 15 software measurement datasets obtained from several high-assurance systems. In addition, to a unique insight into the costbased performance of defection prediction models, this study is one of the first to use misclassification cost as a parameter during the model-training process. The practical appeal of this research is that it provides a software quality practitioner with a clear process for how to consider (during model training) and analyze (during model evaluation) the cost-based performance of a defect prediction model. RUS is ranked as the best cost-sensitive technique among those considered in this study.