Risk Prediction with Regression in Global Software Development using Machine Learning Approach: A Comparison of Linear and Decision Tree Regression

Asim Iftikhar; Shahrulniza Musa; Muhammad Alam; Rizwan Ahmed; Tariq Rahim Soomro; Mazliham Mohd Su’ud

首页> 外文期刊>Journal of computer sciences >Risk Prediction with Regression in Global Software Development using Machine Learning Approach: A Comparison of Linear and Decision Tree Regression

【24h】

Risk Prediction with Regression in Global Software Development using Machine Learning Approach: A Comparison of Linear and Decision Tree Regression

机译：使用机器学习方法的全球软件开发中的回归风险预测：线性和决策树回归的比较

获取原文

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相似文献
相关主题

摘要

Software development through teams at different geographical locations is a trend of modern era, which is not only producing good results without costing lot of money, but also productive in relation to its cost with low risk and high return. This shift of perception of working in a group rather than alone is getting stronger day by day and has become an important planning tool and part of their business strategy. Due to this phenomenal shift the development processes have become complex and chances of risks have been increased. The utilization of Machine learning to manage risk is helpful when taking care of and evaluating data. In this research regression approaches like Linear Regression and Tree Regression have been implemented to predict the responses of risks involved in global software development. Comparative analysis has also been performed between these two algorithms to determine the highest accuracy algorithms. The results indicate that Fine tree regression, which is one of techniques of decision tree regression, gave better results in terms of goodness of fit measures as compared to linear regression model fitted to examine the relationship of cost, time and resource related risk with the overall risk of global software development projects.

机译：通过不同地理位置的团队的软件开发是现代时代的趋势，这不仅在没有耗费大量资金的情况下产生了良好的结果，而且还与低风险和高回报的成本有效。这种在一个团体中工作而不是独自在一起的感知的转变是在一天中更强烈，并已成为一个重要的规划工具和部分业务战略。由于这种现象，发展过程变得复杂，风险的机会增加了。在处理和评估数据时，利用机器学习来管理风险是有用的。在本研究中，已经实施了线性回归和树回归等回归方法，以预测全球软件开发的风险的响应。在这两种算法之间也进行了比较分析以确定最高精度算法。结果表明，与决策树回归的技术之一，这是与拟合措施的良好效率相比，与拟合成本，时间和资源相关风险的关系相比，在拟合措施的良好方面产生了更好的结果。全球软件开发项目的风险。

著录项

来源
《Journal of computer sciences》 |2021年第2期|共23页
作者
Asim Iftikhar; Shahrulniza Musa; Muhammad Alam; Rizwan Ahmed; Tariq Rahim Soomro; Mazliham Mohd Su’ud;
展开▼
作者单位

展开▼
收录信息
原文格式 PDF
正文语种
中图分类
关键词
Global Software DevelopmentRisk Management in Global Software DevelopmentMachine LearningLinear RegressionDecision Tree Regression;

机译：全球软件开发iss管理在全局软件开发机器中学习线性回归树回归;

相似文献

外文文献
中文文献
专利

1. A land use regression model for ambient ultraflne particles in Montreal, Canada: A comparison of linear regression and a machine learning approach [J] . Scott Weichenthal, Keith Van Ryswyk, Alon Goldstein, Environmental research . 2016,第apra期

机译：加拿大蒙特利尔的环境超微粒子的土地利用回归模型：线性回归与机器学习方法的比较
2. Spatial prediction of landslides using a hybrid machine learning approach based on Random Subspace and Classification and Regression Trees [J] . Binh Thai Pham, Prakash Indra, Dieu Tien Bui Geomorphology . 2018,第FEBa15期

机译：基于随机子空间和分类回归树的混合机器学习方法在滑坡空间预测中的应用
3. Data mining methods in the prediction of Dementia: A real-data comparison of the accuracy, sensitivity and specificity of linear discriminant analysis, logistic regression, neural networks, support vector machines, classification trees and random forests [J] . Jo?o Maroco, Dina Silva, Ana Rodrigues, BMC research notes . 2011,第1期

机译：痴呆症预测中的数据挖掘方法：线性判别分析，逻辑回归，神经网络，支持向量机，分类树和随机森林的准确性，敏感性和特异性的真实数据比较
4. Extraction of Heart Rate from PPG Signal: A Machine Learning Approach using Decision Tree Regression Algorithm [C] . Shikder Shafiul Bashar, Md. Sazal Miah, A.H.M. Zadidul Karim, International Conference on Electrical Information and Communication Technology . 2019

机译：从PPG信号中提取心率：一种使用决策树回归算法的机器学习方法
5. A COMPARISON OF SIX MODELS FOR PREDICTING CORPORATE BANKRUPTCY: MULTIPLE LINEAR REGRESSION ANALYSIS, MULTIPLE LINEAR DISCRIMINANT ANALYSIS, STEPWISE REGRESSION ANALYSIS, STEPWISE DISCRIMINANT ANALYSIS, MULTIPLE LINEAR REGRESSION ANALYSIS WITH RIDGE REGRESSION, AND MULTIPLE LINEAR DISCRIMINANT ANALYSIS WITH BIASED MINIMUM CHI-SQUARE RULE [D] . MAPP, JOHNNIE ALBERT. 1981

机译：六种预测公司破产的模型的比较：多个线性回归分析，多个线性判别分析，逐步回归分析，逐步判别分析，多个带岭点回归的线性回归分析，以及多个线性离散
6. Data mining methods in the prediction of Dementia: A real-data comparison of the accuracy sensitivity and specificity of linear discriminant analysis logistic regression neural networks support vector machines classification trees and random forests [O] . João Maroco, Dina Silva, Ana Rodrigues, 2011

机译：痴呆症预测中的数据挖掘方法：线性判别分析逻辑回归神经网络支持向量机分类树和随机森林的准确性敏感性和特异性的真实数据比较
7. A land use regression model for ambient ultrafine particles in Montreal, Canada: A comparison of linear regression and a machine learning approach [O] . Weichenthal Scott, Ryswyk Keith Van, Goldstein Alon, 2016

机译：加拿大蒙特利尔的环境超细颗粒土地利用回归模型：线性回归与机器学习方法的比较

Risk Prediction with Regression in Global Software Development using Machine Learning Approach: A Comparison of Linear and Decision Tree Regression

摘要

著录项

相似文献

相关主题

期刊订阅