Real-time scoring with nested predictive models for missing value imputation
By chberger on Jan 23, 2010
So what do you do? Easy! You build another model, estim_income and nest that model inside the ODM attrition_model when scoring.
See this example where we select the 10 customers who are most likely to attrite based solely on: age, gender, annual_income, and zipcode. In addition, since annual_income is often missing, perform null/missing value imputation for the annual_income attribute using all of the customer demographics.
SELECT * FROM (
SELECT cust_name, cust_contact_info,
rank() over (ORDER BY
USING age, gender, zipcode,
PREDICTION(estim_income USING *))
as annual_income) DESC) as cust_rank
WHERE cust_rank < 11;
As the first model scores, the second model estim_income performs Oracle's null/missing value imputation for the annual_income attribute using all of the customer demographics/
Voilà! A complex multi-model problem made easy with Oracle Data Mining and its 12 in-database data mining functions combined with the power of SQL and the Oracle Database.