An abnormality occurrence presumption apparatus which presumes the occurrence of an abnormality in a telescopic cover attached to a machine tool performs supervised learning on the basis of a feature amount extracted from a physical quantity acquired during an operation of the machine tool and information related to an abnormality occurring in the telescopic cover, and stores the result of the learning. The abnormality occurrence presumption apparatus presumes an abnormality that may occur in the telescopic cover during the operation of the machine tool on the basis of the result of the learning and the feature amount extracted from the physical quantity.