Feature generator, feature generator and feature generator

摘要

The table acquisition means 381 acquires a first table including the prediction target and the first attribute, and a second table including the second attribute. The receiving means 382 accepts a similarity function used for calculating the similarity between the first attribute and the second attribute, and a condition for the similarity. The feature amount generating means 383 uses a similarity function, and the first attribute value including the value of the first attribute whose similarity calculated by the value of the first attribute and the value of the second attribute satisfies the condition. It is represented by the join condition for joining the record of the table and the record of the second table containing the value of the second attribute, the aggregation method for multiple records in the second table, and the column to be aggregated. The feature quantity candidates that can affect the prediction target are generated by using the aggregation conditions. The feature amount selection means 384 selects the optimum feature amount for prediction from the feature amount candidates.