The main purpose of this thesis is to create a model like Earned Value Management (EVM) model in the Project Management for better forecasting. Some machine learning concepts will be used to better predict the project duration and minimize the cost. Traditional EVM model formulas to track Projects progress relies on too many assumptions and simplifications. This oversimplification can affect the accuracy of the forecasting which can cause delay and in turn increase project costs. There is also bias related to human perceptions in the EVM model which must be eliminated. The goal is to develop a new dynamic monitoring and optimization tool to track progress of the project.