×

Method and system for predicting customer behavior based on data network geography

  • US 7,660,459 B2
  • Filed: 06/12/2001
  • Issued: 02/09/2010
  • Est. Priority Date: 06/12/2001
  • Status: Expired due to Fees
First Claim
Patent Images

1. A data processing machine implemented method of selecting data sets for use with a predictive algorithm based on data network geographical information, comprising data processing machine implemented steps of:

  • generating, by the data processing machine, a first statistical distribution of a training data set;

    generating, by the data processing machine, a second statistical distribution of a testing data set;

    using, by the data processing machine, the first statistical distribution and the second statistical distribution to identify a discrepancy between the first statistical distribution and the second statistical distribution with respect to the data network geographical information by comparing at least one of the first statistical distribution and the second statistical distribution to a statistical distribution of a customer database to determine if at least one of the training data set and the testing data set are geographically representative of a customer population represented by the customer database;

    modifying, by the data processing machine, selection of entries in one or more of the training data set and the testing data set based on the discrepancy between the first statistical distribution and the second statistical distribution; and

    using the modified selection of entries by the predictive algorithm.

View all claims
  • 1 Assignment
Timeline View
Assignment View
    ×
    ×