Risk Prediction Applied to Global Software Development using Machine Learning Methods

Software companies aim to develop high-quality software projects with the best global resources at cost. To achieve this development (GSD), an approach should be used which adopts work on across multiple distributed locations, and is also known as development. When attempt implement GSD, they face numerous challenges owing nature of GSD its differences from traditional methods. The objectives study were identify top factors that affect overall success or failure a project using exploratory data analysis find relationships between these factors, compare risk prediction models use machine learning classification techniques such logistic regression, decision tree, random forest, support vector machine, K-nearest neighbors, Naive Bayes. findings are follows: in 18 influencing listed; experiments show regression forest provide results, accuracy 89% 85%, respectively, area under curve 73% 71%, respectively.