Predict software project completion time and cost using XGBoost

Abstract

Nowadays, with the rapid development of information technology, managing costs and time to complete software projects has become an urgent issue. To be able to manage software projects, the need to predict costs and completion times is extremely important. Traditional methods often use EVM earned value management to predict project costs and completion times. However, this method often does not achieve very high accuracy when the data has a lot of noise. In recent years, machine learning methods have emerged as a useful solution for leveraging past data to predict future values. In this study, we propose to use the XGBoost machine learning model to predict project costs and completion time. Experimental results show that XGBoost has the potential to solve this problem.