Extensibility for sales predictor (SPE)

摘要

Disclosed are methods and systems for implementing extensibility in sales prediction engines. An extensibility framework may be used to modify the metadata schema of the data used by the sales prediction engine to account for extended attributes and entities. The sales prediction engine is also modified to recognize the extended attributes and entities so that a user will be able to create new rules and train new models based on the extended attributes and entities.

主权项

1. A computer-based method for extending attributes for a predictive analysis engine, comprising:
maintaining a database table for a database entity, the database table corresponding to a metadata schema that defines one or more original attribute columns and one or more unused extension columns for the database entity, the one or more unused extension columns providing extensibility of the database entity for a new attribute not defined in the one or more original attribute columns of the database entity; receiving from an interface a definition of the new attribute for the database entity; modifying, using a server computer system, a first version of the database entity to a second version of the database entity, the second version of the database entity comprising the new attribute that does not exist in the first version by:
reviewing the one or more unused extension columns for the first version of the database entity,identifying an unused extension column from among the one or more unused extension columns for the first version of the database entity, andediting the metadata schema for the database table to map the identified unused extension column to the new attribute to generate the second version of the database entity; identifying the new attribute to a business intelligence server, wherein a mapping is performed in the business intelligence server to correlate a logical representation of the database entity to the metadata schema of the database table for the second version of the database entity to create database queries to include the new attribute; modifying a user interface of the predictive analysis engine to recognize the new attribute for the database entity; interfacing with the predictive analysis engine to perform predictive analysis using the new attribute and data for the new attribute retrieved with the database queries created in the business intelligence server; and using the predictive analysis engine to generate recommendations based at least in part on the new attribute by using one or more new rules or one or more new models, wherein the one or more new rules and the one or more new models comprise the new attribute.