Forecasting Outcomes Based on Analysis of Text Strings

Abstract

A method and a processing device are provided for forecasting whether a record of data for an individual is associated with an outcome. Whether an n-gram associated with one of a group of predictors matches an n-gram included in the record of data is determined. When the n-gram included with the one of the group of predictors matches the n-gram in the record of data, a prediction is made as to whether the record of data is associated with the outcome based on a value assigned to the one of the group of predictors.

1 . A method for forecasting whether a plurality of records are associated with an outcome, the method comprising:
 for a first record:
 a) obtaining a pre-assigned classifier associated with the first record; 
 b) analyzing characters in the first record to determine n-grams appearing in the first record; 
 c) incrementing a record counter associated with each n-gram determined to be in the first record; 
 d) determining whether a pre-assigned classifier is associated with a possible outcome; and 
 e) if the pre-assigned classifier is determined to be associated with a possible outcome, incrementing an outcome counter associated with each n-gram in the first record; 
   if more records are available, accessing a next record and carrying out steps (a)-(e);   determining a predictive value associated with each n-gram based on a respective outcome counter and a record counter associated with each respective n-gram; and   creating an ordered set of predictors corresponding to n-grams appearing in a minimum number of records.