Ml/Dl Analytical Approaches to Assist Software Project Managers: Dashboard

Abstract

Companies frequently turn to project management systems for advice with the ongoing data growth caused by stakeholders throughout a product life cycle. The team will be able to communicate more effectively, plan their next moves, have an overview of the current project state, and act before the projections are delivered with project-oriented business intelligence approaches. These technologies are becoming even more beneficial as agile working mindsets proliferate. It establishes a fundamental concept of how the project should function so that the implementation is simple to use and follow. Teams and the potential for economic generation are held back by the high project failure rates brought on by inadequate project planning. The advancement of Machine Learning (ML) and Deep Learning (DL) methodologies has greatly benefited business and project management. To assist project managers in planning their projects and evaluating risks, we have examined techniques that help them anticipate potential hazards when planning their project milestones based on their prior experiences. The system's three components are the database, the web-based platform, and the machine learning core. To do this, we applied a variety of artificial intelligence techniques. Our system must be able to do risk analysis as quickly as is practical and provide project managers with recommendations using the least amount of data necessary. This article thoroughly analyses much research that has addressed the use of machine learning in software project management. This study thoroughly analyses the literature on three critical subjects: software project management, machine learning, and methods from Web Science, Science Directs, and IEEE Explore. There are 111 papers divided into four categories in these three archives. Our contribution also offers context and a broader viewpoint, essential for potential project risk management initiatives.