Methods of Proactive Management of Complex Projects Based on Neural Networks

In this paper, the results of research into the use of two methods of proactive change management in complex IT projects are presented based on the consideration of deviations in two key parameters of projects - in time and cost. Forecast estimates of the status of projects as a result of impacts of changes in the external and internal environment of projects are modeled using neural networks of deep training. This approach allows to predict the level of changes in the results of the project activity at any time during the implementation of projects. The evaluation of the results of modeling the effects of changes on project parameters is carried out taking into account the context characteristics of projects, including resource allocations both in time and in project work, cost allocations, etc.