Analytical methods and tools for determining needs of orphan policyholders

• US 10,026,129 B1
• Filed: 12/19/2014
• Issued: 07/17/2018
• Est. Priority Date: 12/23/2013
• Status: Active Grant

• Current Assignee: Massachusetts Mutual Life Insurance Company
• Original Assignee: Massachusetts Mutual Life Insurance Company
• Inventors: Ross, Gareth, Walker, Tricia
• Primary Examiner(s): Niquette, Robert R
• Assistant Examiner(s): KING JR., JOSEPH W
• Application Number:
  US14/576,440
• Time in Patent Office: 1,306 Days
• Field of Search: None
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 40/08 Insurance

Abstract

A method for matching insurance products to orphan policyholders may enable an insurance company to automatically identify sales value and propensity to sales of a list of orphan policyholders, among other characteristics, by using collaborative filtering techniques and learning algorithms. The method may further enable automated marketing and sales and may reduce internal costs which may be further transferred to customers as a discount and provide a competitive edge within the insurance industry.

Claims

1. A computer-executed method comprising:

receiving, by an analytical engine of a computer and from a first internal database configured to store profile data associated with one or more users, profile data associated with a first user;

identifying, by the analytical engine of the computer, that the first user is not associated with a first employee based on the profile data associated with the first user;

crawling, by the analytical engine of the computer, a plurality of social networking databases to collect additional data associated with the first user;

receiving, by the analytical engine of the computer, from a second internal database that is configured to store product data and purchase history data corresponding to the one or more users, product data and purchase history data corresponding to the first user;

generating, by the analytical engine of the computer, an analytical model that determines recommended products matching potential needs associated with the one or more users using collaborative filtering techniques by analyzing user profiles, the product data, the additional data, and the purchase history data associated with the one or more users;

determining, by the analytical engine of the computer, a recommended product for the first user by executing the analytical model based on the first user profile, the product data, the additional data obtained from the crawling, and the purchase history data associated with the first user; and

automatically initiating, by the computer, an automated communication session with a computing device operated by the first user to offer the recommended product to the first user by transmitting an email message containing a hyperlink directing the first user to a website displaying data associated with the recommended product.

2. The method of claim 1, wherein the profile data includes at least one of age, geography, total insurance, gender, months as a customer, income, and life events.

3. The method of claim 1, wherein the purchase history data includes at least one of an address, tax records, purchase history, and credit history of the first user.

4. The method of claim 1, wherein the collaborative filtering technique is a K-Nearest Neighbor algorithm.

5. The method of claim 1, wherein the collaborative filtering technique is UV decomposition.

6. The method of claim 1, further comprising training the analytical model, by the analytical engine of the computer, by executing a stochastic gradient descent algorithm.

7. A system comprising:

a computer readable memory having stored thereon computer executable instructions for matching a product to a user; and

a computer coupled to the memory, the computer executing the instructions performing steps including;

receiving, by an analytical engine of a computer and from a first internal database configured to store profile data associated with one or more users, profile data associated with a first user;

identifying, by the analytical engine of the computer, that the first user is not associated with a first employee based on the profile data associated with the first user;

crawling, by the analytical engine of the computer, a plurality of social networking databases to collect additional data associated with the first user;

receiving, by the analytical engine of the computer, from a second internal database that is configured to store product data and purchase history data corresponding to the one or more users, product data and purchase history data corresponding to the first user;

generating, by the analytical engine of the computer, an analytical model that determines recommended products matching potential needs associated with the one or more users using collaborative filtering techniques by analyzing user profiles, the product data, the additional data, and the purchase history data associated with the one or more users;

determining, by the analytical engine of the computer, a recommended product for the first user by executing the analytical model based on the first user profile, the product data, the additional data obtained from the crawling web-crawling, and the purchase history data associated with the first user; and

automatically initiating, by the computer, an automated communication session with a computing device operated by the first user to offer the recommended product to the first user by transmitting an email message containing a hyperlink directing the first user to a website displaying data associated with the recommended product.

8. The system of claim 7, wherein the profile data includes at least one of age, geography, total insurance, gender, months as a customer, income, and life events.

9. The system of claim 7, wherein the purchase history data includes at least one of an address, tax records, purchase history, and credit history of the first user.

10. The system of claim 7, wherein the collaborative filtering technique is a K-Nearest Neighbor algorithm.

11. The system of claim 7, wherein the collaborative filtering technique is UV decomposition.

12. The system of claim 7, further comprising training the analytical model, by the analytical engine of the computer, by executing a stochastic gradient descent algorithm.