Forecasting a volume associated with an outcome based on analysis of text strings

摘要

A method and a device are provided for forecasting a volume associated with an outcome. A determination is made with respect to whether n-grams associated with a group of predictors matches n-grams included in records of data. A probability is estimated with respect to each of the records of data being associated with the outcome based on a value assigned to a respective one of the group of predictors when the n-gram associated with the respective one of the group of predictors is determined to match the n-gram included in a respective one of the records of data. An estimate of the volume associated with the outcome is calculated based on the estimated probabilities.