| 摘要 |
A time series prediction apparatus 10 according to the present invention, which is an information processing apparatus for predicting a trend of time series data pertaining to events, calculates relevance, which is an index for indicating the intensity of causal relationships between events, on the basis of time series data related to each of a plurality of events including an event to be predicted, and time series data related to the causal relationship between the events; and predicts a trend of the time series data related to the events on the basis of the calculated relevance. The time series prediction apparatus 10 calculates the relevance by using a co-occurrence frequency of terms related to the events in the time series data related to the causal relationship between the events. The time series prediction apparatus 10 constructs a plurality of prediction models for predicting a trend of time series data related to the event to be predicted on the basis of the time series data related to an event having a causal relationship with the event to be predicted, and integrates respective prediction results of the prediction models by weighting each prediction model according to relevance. |
