TRANSPORTATION MEANS PREDICTION MODEL GENERATION DEVICE, TRANSPORTATION MEANS PREDICTION MODEL GENERATION METHOD AND TRANSPORTATION MEANS PREDICTION MODEL GENERATION PROGRAM

摘要

PROBLEM TO BE SOLVED: To generate a prediction model capable of predicting the determination of transportation means by a user with higher accuracy even in the situation where right-answer data is not sufficiently given.SOLUTION: A case generation function 20 classifies segments stored in a segment DB 50 into a training case collection T with right-anser labels and a non-labeled case collection U without right-answer labels. A prediction model generation function 30 generates a prediction model C from the training case collection T, predicts a label to be applied to each case in the non-labeled case collection U, calculates certainty of the predicted label, adds cases of which the certainty is equal to or higher than a threshold value , to the training case collection T and generates a new prediction model C iteratively until an end condition is satisfied. Thus, even in the situation where right-answer data is not sufficiently given, the prediction model is generated by using data to which the right-answer label is not given, such that prediction accuracy of the prediction model can be improved and that transportation mode determination accuracy of a user can be improved.