Over the past ten years, agile techniques have completely changed the software development landscape. More and more, data analytics is becoming a typical tool for enhancing development cycles as big data grows in popularity. The planning and assessment of project management is highly valued in activities pertaining to project performance. Without a sensible and workable plan, managing projects effectively is challenging. In other words, over the last five years, a wave of data analytics has swept over all industries, transforming engineering management practices in a number of them and influencing research at universities. To build, test, polish, and document a specific software feature, an agile method involves sprints. By detecting several patterns and combining the total findings, a realistic image of the future topography of project management is offered. By using analytical and statistical methods, that is achieved. Lastly, our results show that machine learning-based project risk assessment is more successful in lowering project failure rates and increasing project success rates. It also provides an alternative method to efficiently increase the production ratio for growth and decrease the project failure probability. It also simplifies the process of analysing software failure prediction in terms of accuracy.
Data Analytics, Agile, Artificial Intelligence