Prediction device, learning device, prediction method, learning method, prediction program, and learning program

The purpose of the present invention is to improve prediction accuracy in a prediction model that predicts a phase fraction within a prescribed temperature range on the basis of a material composition. The prediction device has a learning model obtained by learning using learning data in which a material composition of a material to be learned and a phase fraction of the material to be learned at each temperature within a predetermined temperature interval are associated. The learning-completed model is configured so as to predict a phase fraction at an (i + 1)-th temperature using a phase fraction predicted by the learning-completed model for temperatures up to the i-th temperature within the predetermined temperature interval, and to predict a phase fraction at the (i + 1)-th temperature by inputting a material composition of a material to be predicted into the learning-completed model. I is an integer greater than or equal to 1, and the phase fraction of the material to be predicted at each temperature wit