State Farm Mutual Automobile Insurance Company (20240281894). METHOD OF CONTROLLING FOR UNDESIRED FACTORS IN MACHINE LEARNING MODELS simplified abstract

METHOD OF CONTROLLING FOR UNDESIRED FACTORS IN MACHINE LEARNING MODELS

Organization Name

State Farm Mutual Automobile Insurance Company

Inventor(s)

Jeffrey S. Myers of Normal IL (US)

Kenneth J. Sanchez of San Francisco CA (US)

Michael L. Bernico of Bloomington IL (US)

METHOD OF CONTROLLING FOR UNDESIRED FACTORS IN MACHINE LEARNING MODELS - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240281894 titled 'METHOD OF CONTROLLING FOR UNDESIRED FACTORS IN MACHINE LEARNING MODELS

The abstract describes a method of training and using a machine learning model that controls for undesired factors to analyze new data, such as evaluating an insurance applicant based on an image without considering factors like age, sex, ethnicity, and race.

• Trained neural network correlates aspects of an applicant's appearance with personal and health-related characteristics.
• Undesired factors like age, sex, ethnicity, and race are excluded from the analysis.
• The model analyzes an image of the insurance applicant and suggests an appropriate insurance premium based only on desired factors.

Potential Applications: This technology can be applied in the insurance industry for underwriting processes to determine appropriate premiums based on objective factors rather than potentially biased characteristics.

Problems Solved: This technology addresses the issue of bias in decision-making processes by excluding undesired factors from the analysis, leading to fairer and more objective outcomes.

Benefits: The technology can lead to more equitable insurance premiums, reduce the impact of bias in decision-making, and improve the overall fairness of underwriting processes.

Commercial Applications: Title: "Fair Underwriting Technology for Insurance Industry" This technology can be commercially used by insurance companies to streamline underwriting processes, improve fairness in premium calculations, and enhance customer satisfaction.

Prior Art: Research on bias mitigation in machine learning models and fairness in decision-making processes can provide insights into prior art related to this technology.

Frequently Updated Research: Stay updated on advancements in bias mitigation techniques in machine learning models, fairness in decision-making algorithms, and applications of AI in the insurance industry.

Questions about Fair Underwriting Technology: 1. How does this technology address bias in decision-making processes? This technology addresses bias by excluding undesired factors from the analysis, leading to fairer outcomes. 2. What are the potential implications of using this technology in the insurance industry? Using this technology can lead to more equitable insurance premiums, reduce bias, and improve customer satisfaction.

Original Abstract Submitted

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 analysis 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.