at least one memory configured to store instructions; and

at least one processor configured to execute the instructions to perform operations comprising:

acquiring input data;

generating, by use of a neural network, condition data that indicate one or more conditions satisfied by the input data;

determining, as prediction data associated with the input data, a value determined based on correct answer data associated with example data that satisfy at least a part of the one or more conditions indicated by the condition data; and

updating a parameter of the neural network, wherein

a plurality of candidate conditions that are candidates of conditions to be included in the condition data are defined,

the prediction data associated with the input data is determined by acquiring, from a storage apparatus storing a plurality of the prediction data in respective a plurality of combinations of one or more candidate conditions of the plurality of candidate conditions, the prediction data associated with a combination of candidate conditions included in the generated condition data.