Determining success factors for project with supervised machine learning

Every year, enormous project failure rates plague business companies across the globe, costing millions of dollars for each failed project. It is critical to understand the factors that influence project success. The goal of this study is to empirically discover the factors that lead to a successful project. This study used data from 469 projects to use three distinct supervised machine learning methods for classification: a) The Support Vector Machine (SVM), 2) The Probit regression, and 3) the Logistic regression. Five factors have been chosen.: Support from the top management, Technical skills, Client’s acceptance, Communication, and Monitoring. The findings of the SVM study revealed that SVM could accurately predict successful and unsuccessful projects. The findings of Logistic and Probit regression revealed that project success is more likely if project managers get appropriate top-level support and if the project team has sufficient technical capabilities. This study also discovered that good communication and control improve the odds of a project's success. However, according to the results of this research, client acceptability is a minor success factor for a project.