New types of multi-component alloys and oxides with high configurational entropy have recently been developed. This new class of materials contains at least five equiatomic elements and has been shown to possess several exciting and unique properties. The aim is to study high-entropy materials as oxygen carriers in chemical looping. Currently, we are working on a framework that uses advanced first-principles methods, machine-learning techniques, and material informatics. We will gather initial data, including computational predictions and experimental observations. This data will then be used to train machine learning algorithms to create models that predict the compositions of high-entropy oxides that are likely to exhibit desirable properties. The evaluation will be done via first-principles methods, which require access to high-performance computer facilities.