Prediction model creation method, prediction method, prediction model creation device, prediction device, prediction model creation program, and prediction program

The prediction accuracy of a learned prediction model is improved by setting an appropriate weight using a cluster classified as a learned clustering model. A method for creating a prediction model for material characteristics, the method comprising: a step for acquiring a learning data set; a step for generating a learned clustering model using the learning data set and a clustering model, and classifying the learning data set into N clusters; calculating the distance between the centers of gravity of each cluster; a step for calculating a weight between the clusters using the distance between the centers of gravity of the clusters and a parameter indicating the characteristics of the learning data set; and for each of the clusters, generating a learned prediction model {Mi} 1 < = i < = N using the clusters and the weights. 通过使用被分类为学习完毕的聚类模型的簇来设定适当的权重，提高学习完毕的预测模型的预测精度。材料特性的预测模型制作方法，具有：取得学习用数据集的步骤；使用所述学习用数据集和聚类模型生成学习完毕聚类模型，并且将所述学习用数据集分类为N个簇的步骤；计算各所述簇的重心间的距离的步骤；使用所述簇的重心间的距离和表示所述学习用数据集的特征的参数，计算所述簇间的权重的步骤；以及对于每个