System and Method for Generating Ultimate Reason Codes for Computer Models

A method for generating ultimate reason codes for computer models comprising:

• receiving a data set at a computer system;
• training a base model with a plurality of reason codes by an ultimate reason code generation engine stored on and executed by the computer system, wherein each reason code includes one or more variables, each of which belongs to only one reason code;
• training by the ultimate reason code generation engine a subsequent model using a subset of the plurality of reason codes;
• determining by the ultimate reason code generation engine whether a high score exists in the base model;
• determining by the ultimate reason code generation engine a scored difference if a high score exists in the base model;
• and
• designating by the ultimate reason code generation engine a reason code having a largest drop of score as an ultimate reason code.

A non-transitory computer-readable medium having computer-readable instructions stored thereon which, when executed by a computer system, cause the computer system to perform the steps of:

• receiving a data set at the computer system;
• training a base model with a plurality of reason codes by an ultimate reason code generation engine stored on and executed by the computer system, wherein each reason code includes one or more variables, each of which belongs to only one reason code;
• training by the ultimate reason code generation engine a subsequent model using a subset of the plurality of reason codes;
• determining by the ultimate reason code generation engine whether a high score exists in the base model;
• determining by the ultimate reason code generation engine a scored difference if a high score exists in the base model;
• and
• designating by the ultimate reason code generation engine a reason code having a largest drop of score as an ultimate reason code.