A system and method for a self-adapting SDWAN to ensure compliance with client requirements. A SDWAN performance analyzer continuously monitors all of the nodes within an SDWAN, receiving a plurality of operational data regarding operational parameters of each node. Based on the operational data, a machine learning algorithm is applied to develop a tree-structure representative of a desired network configuration, based on the real-time state of the network, to ensure compliance with client requirements. The SDWAN performance analyzer can generate configuration commands to send to one or more of the nodes in the SDWAN to reconfigure the operational parameters of the nodes in line with the desired network configuration.