Systems and methods for excluded risk factor predictive modeling

A processor-based method, comprising:

• executing, by a processor, a first predictive machine learning model configured to determine, for each historical application record of a plurality of historical application records stored in a database, a mortality risk rank by inputting the historical application records supplemented by public records and credit risk data identified with an applicant of the respective historical application record received from one or more third party sources into a machine learning model ensemble,
• wherein feature selection for the first predictive machine learning model excludes all clinical assessment attributes of the historical application records, and fits a survival model to the public records and credit risk data to select attributes of the public records and credit risk data with highest importance based on mortality risk as variables of the first predictive machine learning model, wherein the survival model is configured to approximate a survival function that describes probability that an event occurs later than some given time;
• and
• upon receiving information for an electronic application from a user device, wherein the information for the electronic application excludes clinical data for an applicant of the electronic application:
• retrieving, by the processor, public records and credit risk data identified with the applicant of the electronic application;
• executing, by the processor, the first predictive machine learning model to determine a mortality risk score, and to classify the electronic application into one of a first high risk group and a first low risk group based upon the mortality risk score;
• executing, by the processor, a second predictive machine learning model to determine a second risk rank representative of a second user risk attribute, wherein the second risk attribute predicts likelihood of at least one risk factor that can be indicated by clinical data, and to classify the electronic application into one of a second high risk group and a second low risk group based upon the second risk rank;
• and
• when the processor classifies the electronic application into the first low risk group and the second low risk group, generating a user interface that displays information associated with an accelerated application offer.

A system comprising:

• an analytical engine server comprising:
• a first module configured for receiving information for an electronic application from a user device that excludes clinical data for an applicant of the electronic application, and for retrieving public data identified with the applicant of the received electronic application from one or more third party source;
• a second module configured for executing a predictive machine learning model to determine a mortality risk rank for the electronic application and classify the electronic application into a first low risk group or a first high risk group,
• wherein the predictive machine learning model comprises a machine learning model ensemble trained by inputting into the predictive machine learning model a plurality of historical application records, wherein each historical application record is supplemented with public data identified with an applicant of the respective historical application record received from the one or more third party source, wherein feature selection for the predictive machine learning model excludes all clinical assessment attributes of the historical application records and selects attributes of the public data with highest importance based on mortality risk as variables of the first predictive machine learning model;
• a third module configured for executing a smoking propensity predictive machine learning model, wherein the smoking propensity model is configured to estimate a propensity of the applicant of the electronic application to be a smoker and determine a smoking/non-smoking binary target;
• a fourth module configured for executing a prescription drug data predictive machine learning model configured to determine disqualifying medical risks based on information derived from prescription drug fills for the applicant of the electronic application;
• and
• a fifth module configured for generating and presenting a user interface that displays information associated with an accelerated application offer when the analytical engine server classifies the electronic application into the first low risk group, determines the non-smoking binary target, and does not determine the disqualifying medical risk.