A growth analysis system (1) according to an example aspect of the present disclosure, comprising a correlation deriving unit (60) comprising a first neural network that uses growth condition information as input data to output contained component information as output data. The correlation deriving unit (60) causes the first neural network to learn by repeatedly performing deep learning using, as training data, the growth condition information and the contained component information indicating the component contained in the organisms that are actually grown in accordance with the growth condition.