Method of controlling for undesired factors in machine learning models
A method of training and using a machine learning model that controls for consideration of undesired factors which might otherwise be considered by the trained model during its subsequent analyses of new data. For example, the model may be a neural network trained on a set of training images to evaluate an insurance applicant based upon an image or audio data of the insurance applicant as part of an underwriting process to determine an appropriate life or health insurance premium. The model is trained to probabilistically correlate an aspect of the applicant's appearance with a personal and/or health-related characteristic. Any undesired factors, such as age, sex, ethnicity, and/or race, are identified for exclusion. The trained model receives the image (e.g., a “selfie”) of the insurance applicant, analyzes the image without considering the identified undesired factors, and suggests the appropriate insurance premium based only on the remaining desired factors.
1. A computer-implemented method of training and using a first machine learning model that controls for consideration of one or more undesired factors which might otherwise be considered by the first machine learning model when analyzing new data as part of an underwriting process to determine an appropriate insurance premium, the method comprising, via one or more processors:
training the first machine learning model using a first training data set that contains information including the one or more undesired factors;
training a second machine learning model using a second training data set that contains only the one or more undesired factors and one or more relevant interaction terms between the one or more undesired factors; and
combining the first machine learning model and the second machine learning model to eliminate a bias created by the one or more undesired factors from consideration by the first machine learning model prior to employing the first machine learning model to analyze the new data as part of the underwriting process to determine the appropriate insurance premium.
2. The computer-implemented method as set forth m claim 1 , wherein the first machine learning model is a neural network.
3. The computer-implemented method as set forth in claim 1 , wherein the second machine learning model is a linear model.
4. The computer-implemented method as set forth in claim 1 , wherein the new data includes a still image or a video recording of a person applying for life insurance or health insurance.
5. The computer-implemented method as set forth in claim 1 , wherein the new data includes an audio recording of a person applying for life insurance.
6. The computer-implemented method as set forth in claim 1 , wherein the new data includes an image of a piece of property for which a person is applying for property insurance.
7. The computer-implemented method as set forth in claim 1 , wherein the first machine learning model is further trained to analyze the new data as part of the underwriting process to determine one or more appropriate terms of coverage.
8. A computer system configured to train and use a first machine learning model that controls for consideration of one or more undesired factors which might otherwise be considered by the first machine learning model when analyzing new data as part of an underwriting process to determine an appropriate insurance premium, the computer system comprising one or more processors configured to:
train the first machine learning model using a training data set that contains information including the one or more undesired factors;
train a second machine learning model using a second training data set that contains only the one or more undesired factors and one or more relevant interaction terms between the one or more undesired factors; and
combine the first machine learning model and the second machine learning model to eliminate a bias created by the one or more undesired factors from consideration by the first machine learning model prior to employing the first machine learning model to analyze the new data as part of the underwriting process to determine the appropriate insurance premium.
9. The computer system as set forth in claim 8 , wherein the first machine learning model is a neural network.
10. The computer system as set forth in claim 8 , wherein the second machine learning model is a linear model.
11. The computer system as set forth in claim 8 , wherein the new data includes a still image or a video recording of a person applying for life insurance or health insurance.
12. The computer system as set forth in claim 8 , wherein the new data includes an audio recording of a person applying for life insurance.
13. The computer system as set forth in claim 8 , wherein the new data includes an image of a piece of property for which a person is applying for property insurance.
14. The computer system as set forth in claim 8 , wherein the machine learning model is further trained to analyze the new data as part of the underwriting process to determine one or more appropriate terms of coverage.
15. A computer-implemented method of training and using a machine learning model that controls for consideration of one or more undesired factors which might otherwise be considered by the machine learning model when analyzing new data as part of an underwriting process to determine an appropriate insurance premium, the method comprising, via one or more processors:
training the machine learning model using a first training data set that contains information including the one or more undesired factors;
training the machine learning model using a second training data set that contains only the one or more undesired factors and one or more relevant interaction terms between the one or more undesired factors to identify the one or more undesired factors and the one or more relevant interaction terms between the one or more undesired factors; and
instructing the machine learning model to not consider the identified one or more undesired factors while analyzing the new data as part of the underwriting process to determine the appropriate insurance premium.
16. The computer-implemented method as set forth in claim 15 , wherein the machine learning model is a neural network.
17. The computer-implemented method as set forth in claim 15 , wherein the new data includes a still image or a video recording of a person applying for life insurance or health insurance.
18. The computer-implemented method as set forth in claim 15 , wherein the new data includes an audio recording of a person applying for life insurance.
19. The computer-implemented method as set forth in claim 15 , wherein the new data includes an image of a piece of property for which a person is applying for property insurance.
20. The computer-implemented method as set forth in claim 15 , wherein the machine learning model is further trained to analyze the new data as part of the underwriting process to determine one or more appropriate terms of coverage.