An input data generation system is an input data generation system generating input data for machine learning for predicting the properties of a material based on a raw material having a known structure, and includes at least one processor, in which at least one processor acquires partial structure data indicating a partial structure from a database, receives at least the input of raw material structure data for specifying the structure of the raw material and blending ratio data indicating a ratio of the blending of the raw material, generates partial structure input data indicating the partial structure existing in the structure of the raw material, on the basis of the partial structure data and the raw material structure data, generates input data by reflecting the blending ratio data on the partial structure input data of the raw material, and inputs the input data to a machine learning model.