The limited impact of individual developer data on software defect prediction

Previous research has provided evidence that a combination of static code metrics and software history metrics can be used to predict with surprising success which files in the next release of a large system will have the largest numbers of defects. In contrast, very little research exists to indicate whether information about individual developers can profitably be used to improve predictions. We investigate whether files in a large system that are modified by an individual developer consistently contain either more or fewer faults than the average of all files in the system. The goal of the investigation is to determine whether information about which particular developer modified a file is able to improve defect predictions. We also extend earlier research evaluating use of counts of the number of developers who modified a file as predictors of the file’s future faultiness. We analyze change reports filed for three large systems, each containing 18 releases, with a combined total of nearly 4 million LOC and over 11,000 files. A buggy file ratio is defined for programmers, measuring the proportion of faulty files in Release R out of all files modified by the programmer in Release R-1. We assess the consistency of the buggy file ratio across releases for individual programmers both visually and within the context of a fault prediction model. Buggy file ratios for individual programmers often varied widely across all the releases that they participated in. A prediction model that takes account of the history of faulty files that were changed by individual developers shows improvement over the standard negative binomial model of less than 0.13% according to one measure, and no improvement at all according to another measure. In contrast, augmenting a standard model with counts of cumulative developers changing files in prior releases produced up to a 2% improvement in the percentage of faults detected in the top 20% of predicted faulty files. The cumulative number of developers interacting with a file can be a useful variable for defect prediction. However, the study indicates that adding information to a model about which particular developer modified a file is not likely to improve defect predictions.     

基于两种统计模型的软件缺陷预测

采集软件研发过程中可能与缺陷有关的过程数据或产品数据,对软件缺陷数量进行预测,达到对软件质量的把控。采用LASSO进行特征值选择确定最佳影响因子集合,采用线性模型和贝叶斯网络模型分别对样本数据进行预测,说明两种模型的因子分析过程和模型构建过程,采用R语言进行编码实现。通过预测结果的对比验证了当数据经过二次主观加工后,采用线性模型的预测结果比贝叶斯网络预测结果更准确。     

A critique of software defect prediction models

Many organizations want to predict the number of defects (faults) in software systems, before they are deployed, to gauge the likely delivered quality and maintenance effort. To help in this numerous software metrics and statistical models have been developed, with a correspondingly large literature. We provide a critical review of this literature and the state-of-the-art. Most of the wide range of prediction models use size and complexity metrics to predict defects. Others are based on testing data, the “quality” of the development process, or take a multivariate approach. The authors of the models have often made heroic contributions to a subject otherwise bereft of empirical studies. However, there are a number of serious theoretical and practical problems in many studies. The models are weak because of their inability to cope with the, as yet, unknown relationship between defects and failures. There are fundamental statistical and data quality problems that undermine model validity. More significantly many prediction models tend to model only part of the underlying problem and seriously misspecify it. To illustrate these points the Goldilock's Conjecture, that there is an optimum module size, is used to show the considerable problems inherent in current defect prediction approaches. Careful and considered analysis of past and new results shows that the conjecture lacks support and that some models are misleading. We recommend holistic models for software defect prediction, using Bayesian belief networks, as alternative approaches to the single-issue models used at present. We also argue for research into a theory of “software decomposition” in order to test hypotheses about defect introduction and help construct a better science of software engineering     

Studying just-in-time defect prediction using cross-project models

Unlike traditional defect prediction models that identify defect-prone modules, Just-In-Time (JIT) defect prediction models identify defect-inducing changes. As such, JIT defect models can provide earlier feedback for developers, while design decisions are still fresh in their minds. Unfortunately, similar to traditional defect models, JIT models require a large amount of training data, which is not available when projects are in initial development phases. To address this limitation in traditional defect prediction, prior work has proposed cross-project models, i.e., models learned from other projects with sufficient history. However, cross-project models have not yet been explored in the context of JIT prediction. Therefore, in this study, we empirically evaluate the performance of JIT models in a cross-project context. Through an empirical study on 11 open source projects, we find that while JIT models rarely perform well in a cross-project context, their performance tends to improve when using approaches that: (1) select models trained using other projects that are similar to the testing project, (2) combine the data of several other projects to produce a larger pool of training data, and (3) combine the models of several other projects to produce an ensemble model. Our findings empirically confirm that JIT models learned using other projects are a viable solution for projects with limited historical data. However, JIT models tend to perform best in a cross-project context when the data used to learn them are carefully selected.     

Early prediction of merged code changes to prioritize reviewing tasks

Modern Code Review (MCR) has been widely used by open source and proprietary software projects. Inspecting code changes consumes reviewers much time and effort since they need to comprehend patches, and many reviewers are often assigned to review many code changes. Note that a code change might be eventually abandoned, which causes waste of time and effort. Thus, a tool that predicts early on whether a code change will be merged can help developers prioritize changes to inspect, accomplish more things given tight schedule, and not waste reviewing effort on low quality changes. In this paper, motivated by the above needs, we build a merged code change prediction tool. Our approach first extracts 34 features from code changes, which are grouped into 5 dimensions: code, file history, owner experience, collaboration network, and text. And then we leverage machine learning techniques such as random forest to build a prediction model. To evaluate the performance of our approach, we conduct experiments on three open source projects (i.e., Eclipse, LibreOffice, and OpenStack), containing a total of 166,215 code changes. Across three datasets, our approach statistically significantly improves random guess classifiers and two prediction models proposed by Jeong et al. (2009) and Gousios et al. (2014) in terms of several evaluation metrics. Besides, we also study the important features which distinguish merged code changes from abandoned ones.     

基于缺陷分类和缺陷预测的软件缺陷预防

为降低软件缺陷率,对现有的缺陷预测模型进行了优化,同时引入正交缺陷分类方法,并对该方法加以改进,使其能够支持缺陷的原因分析,将缺陷预测与改进的正交缺陷分类方法结合起来,形成一套软件缺陷预防流程并应用在实际项目中.实验结果表明,该成果可以在软件生命周期的各个阶段有效预防缺陷,最大限度地提高软件质量.     

基于贝叶斯网络的克隆代码有害性预测

在软件开发过程中,程序员的复制、粘贴活动会产生大量的克隆代码,而那些发生不一致变化的克隆代码往往对程序是有害的。为了解决该问题,有效地发现程序中的有害克隆代码,提出一种基于贝叶斯网络的克隆有害性预测方法。首先,结合软件缺陷研究领域与克隆演化领域的相关研究成果,提出了两大类表征克隆代码信息的特征,分别是静态特征和演化特征;其次,通过贝叶斯网络核心算法来构建克隆有害性预测模型;最后,预测有害克隆代码发生的可能性。在5款C语言开源软件共99个版本上对克隆有害性预测模型的性能进行评估,实验结果表明该方法能够有效地实现对克隆代码有害性的预测,降低有害克隆代码对软件的威胁,提高软件质量。     

基于PSO-BP的软件缺陷预测模型

软件缺陷检测旨在自动检测程序模块中是否包含缺陷,从而加速软件测试过程,提高软件系统的质量。针对传统软件缺陷预测模型被限制在一定的应用范围而影响其预测的准确性和适用性,提出了一种基于PSO-BP软件缺陷预测模型。该模型运用粒子群优化算法优化BP神经网络的权值和阈值,采用交叉验证的方式进行实验,并与传统的机器学习方法J48和BP神经网络等方法进行了比较。实验结果表明提出的方法具有较高的预测准确性。     

基于不平衡数据集的软件缺陷预测

数据的不平衡性是软件缺陷预测研究中一个严峻且无法规避的问题,为了解决这一问题,本文提出一种利用分布函数合成新样本的过抽样和随机向下抽样相结合的算法。该算法首先对降维后的主成分进行分布函数拟合,然后利用分布函数生成随机数,并对生成的随机数进行筛选,最后与随机向下抽样相结合。实验所用数据取自NASA MDP数据集,并与经典的SMOTE 向下抽样方法进行对比,从G-mean和F-measure值可以看出前者的预测结果明显优于后者,预测精度更高。     

软件缺陷集成预测模型研究

利用单一分类器构造的缺陷预测模型已经遇到了性能瓶颈, 而集成分类器相比单一分类器往往具有显著的性能优势。以构造高效的集成缺陷预测模型为出发点, 比较了七种不同类型集成分类器的算法和特点。在14个基准数据集上的实验显示, 部分集成预测模型的性能优于基于朴素贝叶斯的单一预测模型。其中, 基于投票的集成分类框架具有最优的预测性能以及统计学意义上的性能优势显著性, 随机森林算法次之。Stacking集成框架也具有较强的泛化能力。     

基于深度语义融合的代码缺陷静态检测方法

随着计算机软件规模和复杂度的不断增加,软件中存在的代码缺陷对公共安全形成了严重威胁。针对静态分析工具拓展性差,以及现有方法检测粒度粗、检测效果不够理想的问题,提出了一种基于程序切片和语义特征融合的代码缺陷静态检测方法。首先,对源代码中的关键点进行数据流和控制流分析,并采用基于过程间有限分布子集（IFDS）的切片方法,以获取由多行与代码缺陷相关的语句组成的代码片段;然后,通过词嵌入法获取代码片段语义相关的向量表示,从而在保证准确率的同时选择合适的代码片段长度;最后,利用文本卷积神经网络（TextCNN）和双向门控循环单元（BiGRU）分别提取代码片段中的局部关键特征和上下文序列特征,并将所提方法用于检测切片级别的代码缺陷。实验结果表明,所提方法能够有效检测不同类型的代码缺陷,并且检测效果显著优于静态分析工具Flawfinder;在细粒度的前提下,IFDS切片方法能进一步提高F1值和准确率,分别达到了89.64%和92.08%;与现有的基于程序切片的方法相比,在关键点为应用程序编程接口（API）或变量时,所提方法的F1值分别达到89.69%、89.74%,准确率分别达到92.15%、91....     

The impact of UML modeling on defect density and defect resolution time in a proprietary system

Background: The contribution of modeling in software development has been a subject of debates. The proponents of model-driven development argue that a big upfront modeling requires substantial investment, but it will payoff later in the implementation phase in terms of increased productivity and quality. Other software engineers perceive modeling activity as a waste of time and money without any real contribution to the final software product. Considering present advancement of model-based software development in software industry, we are challenged to investigate the real contribution of modeling in software development. Objective: We analyze the impacts of UML modeling, specifically the production of class and sequence diagrams, on the quality of the code, as measured by defect density, and on defect resolution time. Method: Using data of a proprietary system, we conduct post-mortem analyses to test the difference in defect density between software modules that are modeled and not modeled. Similarly, we test the difference in resolution time between defects that are related to modeled and not modeled functionality. Result: We have found that the production of UML class diagrams and sequence diagrams reduces defect density in the code and the time required to fix defects. These results are obtained after controlling for the effects of co-factors such as code coupling and complexity. Conclusion: The results confirm that not only does the production of UML class diagrams and sequence diagrams possibly help improve the quality of software, but also it possibly help increase the productivity in software maintenance.     

The evolutionary development of roughness prediction models

The vigorous expansion of wind energy power generation over the last decade has also entailed innovative improvements to surface roughness prediction models applied to high-torque milling operations. Artificial neural networks are the most widely used soft computing technique for the development of these prediction models. In this paper, we concentrate on the initial data transformation and its effect on the prediction of surface roughness in high-torque face milling operations. An extensive data set is generated from experiments performed under industrial conditions. The data set includes a very broad set of different parameters that influence surface roughness: cutting tool properties, machining parameters and cutting phenomena. Some of these parameters may potentially be related to the others or may only have a minor influence on the prediction model. Moreover, depending on the number of available records, the machine learning models may or may not be capable of modelling some of the underlying dependencies. Hence, the need to select an appropriate number of input signals and their matching prediction model configuration.A hybrid algorithm that combines a genetic algorithm with neural networks is proposed in this paper, in order to address the selection of relevant parameters and their appropriate transformation. The algorithm has been tested in a number of experiments performed under workshop conditions with data sets of different sizes to investigate the impact of available data on the selection of corresponding data transformation. Data set size has a direct influence on the accuracy of the prediction models for roughness modelling, but also on the use of individual parameters and transformed features. The results of the tests show significant improvements in the quality of prediction models constructed in this way. These improvements are evident when these models are compared with standard multilayer perceptrons trained with all the parameters and with data reduced through standard Principal Component Analysis practice.     

The impact of blockchain on business models in banking

Information Systems and e-Business Management - Blockchain technology is predicted to reshape existing business models of the financial services industry. But although blockchain is often seen as a...     

The impact of background error parameters on heavy rainfall prediction

A heavy rainfall event over the northwest of India is selected to investigate the impact of Atmospheric Infrared Sounder (AIRS)-retrieved temperature and moisture profile assimilation on regional model prediction. The Weather Research and Forecasting (WRF) model and its three-dimensional variational (3D-Var) data assimilation system (WRFDA) is used to assimilate AIRS profiles with tuning of two major background error parameters – viz. length and variance scales. Assimilation of AIRS profiles improves the WRF model analyses, which are closer to the Moderate Resolution Imaging Spectrometer (MODIS) profiles compared to those without assimilation experiment. Results show that within a wide parameter range of length and variance scales, the assimilation of AIRS-retrieved profiles has a positive influence on heavy rainfall prediction. Approximately 9–30, 5–42, and 0.5–3.0% domain average values of improvement are observed after AIRS profile assimilation for different values of length and variance scales in temperature, water vapour mixing ratio, and rainfall prediction, respectively. This study shows that the impact of observations on the WRF model forecast is dependent on the length and variance scale parameters of background error, and lower values of length scale in WRFDA result in degradation of the forecast.     

基于耦合度和PDG混合特征的源代码作者归属预测

为了在语料库中找出源代码的真实作者,提出了一种代码耦合度与程序依赖图特征结合的神经网络模型CPNN来识别源代码作者.首先,使用从源代码中提取的参数、扇入和扇出等特征计算代码的耦合度.其次,从转换的程序依赖图中提取控制和数据依赖项,应用预处理技术将PDG特征转换为具有频率细节的小实例,并且利用逆文档频率技术放大源代码中每...     

基于概率的无监督缺陷预测方法

软件缺陷预测能够提高软件开发和测试的效率,保障软件质量。无监督缺陷预测方法具有不需要标签数据的特点,从而能够快速应用于工程实践中。提出了基于概率的无监督缺陷预测方法—PCLA,将度量元值与阈值的差值映射为概率,使用概率评估类存在缺陷的可能性,然后再通过聚类和标记来完成缺陷预测,以解决现有无监督方法直接根据阈值判断时对阈值比较敏感而引起的信息丢失问题。将PCLA方法应用在NetGen和Relink两组数据集,共7个软件项目上,实验结果表明PCLA方法在查全率、查准率、F-measure上相对现有无监督方法分别平均提升4.1%、2.52%、3.14%。     

改进PSO-ISVM算法的软件缺陷预测

提出基于改进的粒子群优化支持向量机方法（PSO-ISVM）的测控软件缺陷预测方法。通过引入代价惩罚系数,定义粒子群优化算法中的适应度函数,利用最小化适应度函数值作为优化目标,排除大量的冗余干扰信息,提高对测控软件有缺陷模块的预测准确度,寻找支持向量机的最优参数。通过仿真实例分析测控软件有效性,并与常用缺陷预测方法进行比较,表明该模型能加快软件缺陷预测速度和提高对有缺陷模块的预测准确度。     

The hybrid grey-based models for temperature prediction

In this paper several grey-based models are applied to temperature prediction problems. Standard normal distribution, linear regression, and fuzzy techniques are respectively integrated into the grey model to enhance the embedded GM(1, 1), a single variable first order grey model, prediction capability. The original data are preprocessed by the statistical method of standard normal distribution such that they will become normally distributed with a mean of zero and a standard deviation of one. The normalized data are then used to construct the grey model. Due to the inherent error between the predicted and actual outputs, the grey model is further supplemented by either the linear regression or fuzzy method or both to improve the prediction accuracy. Results from predicting the monthly temperatures for two different cities demonstrate that each proposed hybrid methodology can somewhat reduce the prediction errors. When both the statistics and fuzzy methods are incorporated with the grey model, the prediction capability of the hybrid model is quite satisfactory. We repeat the prediction problems in neural networks and the results are also presented for comparison.     

基于深度自编码网络的软件缺陷预测方法

软件缺陷预测是提升软件质量的有效方法,而软件缺陷预测方法的预测效果与数据集自身的特点有着密切的相关性。针对软件缺陷预测中数据集特征信息冗余、维度过大的问题,结合深度学习对数据特征强大的学习能力,提出了一种基于深度自编码网络的软件缺陷预测方法。该方法首先使用一种基于无监督学习的采样方法对6个开源项目数据集进行采样,解决了数据集中类不平衡问题;然后训练出一个深度自编码网络模型。该模型能对数据集进行特征降维,模型的最后使用了三种分类器进行连接,该模型使用降维后的训练集训练分类器,最后用测试集进行预测。实验结果表明,该方法在维数较大、特征信息冗余的数据集上的预测性能要优于基准的软件缺陷预测模型和基于现有的特征提取方法的软件缺陷预测模型,并且适用于不同分类算法。