Extracting predictive segments from sampled data
AssigneeCertona Corporation
InventorsGeoffrey J. Hueter, Benjamin S. Farber
Life of this patent
Estimating the term…
Abstract
A system and method is disclosed which predicts the relative occurrence or presence of an event or item based on sample data consisting of samples which contain and samples which do not contain the event or item. The samples also consist of any number of descriptive attributes, which may be continuous variables, binary variables, or categorical variables. Given the sampled data, the system automatically creates statistically optimal segments from which a functional input/output relationship can be derived. These segments can either be used directly in the form of a lookup table or in some cases as input data to a secondary modeling system such as a linear regression module, a neural network, or other predictive system.
Claims22
A computer implemented web-based predictive modeling system to extract predictive segments from sampled data used for predicting subject response, comprising:
- an application client having an end-user interface and a recommendation server having a profiler, comprising a service system to collect sample transactions both with and without an item of interest;
- subject profiles represented as attribute values;
- recommendations to, and collecting response data from, an end use external application;
- an objective function representing the goal of the said external application;
- and
- wherein said system automatically determines the optimal segments;
- whereby the computer implemented web-based predictive modeling system to extract predictive segments from sampled data used for predicting subject response determines the optimal segments and is able to synthesize the functional input-output pairs that are required as a pre-condition for other modeling systems, including being able to create models from any type of sampled data, support for any data type, working with correlated input variables, not requiring expert knowledge or pre-analysis to identify variables or variable bins to create input-output pairs.
A computer implemented web-based predictive modeling method to extract predictive segments from sampled data used for predicting subject response, comprising the steps of:
- providing an application client having an end-user interface and a recommendation server having a profiler, comprising a service system to collect sample transactions both with and without an item of interest, along with associated subject profiles represented as attribute values;
- providing a data collector that feeds outcome and attribute data to a service system;
- having said data collector feed outcome and attribute data to the system, and storing said data in a system database wherein the outcomes include the conversion events for any items that a service customer would like to target to its users;
- providing a profiling module which then builds the predictive segments for each item based on the outcomes and attributes of each user transaction;
- and
- storing the resulting models in a model database;
- whereby during operation the models are either accessed directly from the model database or cached into web servers for faster processing and higher system throughput.
A computer implemented web-based predictive modeling method to extract predictive segments from sampled data used for predicting subject response, comprising the steps of:
- providing segmentation attributes and sampled data;
- and
- analyzing the distribution of sampled data.
A computer implemented web-based predictive modeling system to extract predictive segments from sampled data used for predicting subject response, comprising:
- an application client having an end-user interface and a recommendation server having a profiler, comprising a service system to take requests from an end use external application and return recommended items;
- sampled data consisting of transactions both with and without items of interest, along with associated subject profiles represented as attribute values;
- recommendations to, and collecting response data from, an end use external application;
- an objective function representing the desired subject response of the said external application;
- and
- wherein said system automatically determines the optimal segments that predict the objective function for the collection of subjects;
- whereby the computer implemented web-based predictive modeling system to extract predictive segments from sampled data used for predicting subject response determines the optimal segments and is able to synthesize the functional input-output pairs that are required as a pre-condition for other modeling systems, including being able to create models from any type of sampled data, support for any data type, working with correlated input variables, not requiring expert knowledge or pre-analysis to identify variables or variable bins to create input-output pairs.
Dependencies are inferred from the claim text.