Patent Issued for Extracting Behaviors And Suggesting Behaviors To Achieve A Desired Credit Score (USPTO 10,803,517)

2020 OCT 27 (NewsRx) -- By a News Reporter-Staff News Editor at Information Technology Business Daily -- From Alexandria, Virginia, NewsRx journalists report that a patent by the inventor Szollar, Suzan (Menlo Park, CA), filed on July 31, 2015, was published online on October 26, 2020.

The patent’s assignee for patent number 10,803,517 is NCR Corporation (Duluth, Georgia, United States).

News editors obtained the following quote from the background information supplied by the inventors: “A credit score is a number used to represent a person’s creditworthiness. Lenders, such as banks and credit card companies, use credit scores to evaluate the potential risk posed by lending money to consumers and to mitigate losses. In other words, lenders use credit scores to determine who qualifies for a loan and who does not. For those that do qualify, a credit score is used to determine at what interest rate and what credit limits a borrower may borrow money.”

As a supplement to the background information on this patent, NewsRx correspondents also obtained the inventor’s summary information for this patent: “System and methods for extracting behaviors and suggesting behaviors to achieve a desired credit score may include receiving, via a network, account data including information regarding currency outlays made by a first sample population; generating, by a computing device, a plurality of behavior patterns based on currency outlay patterns extracted from the account data; receiving, by the computing device, credit score data for the first sample population; formulating, by the computing device, a model for predicting a credit score change; and storing the model on a data storage device. The model may include variables corresponding to each of the plurality of behavior patterns and a likely credit score affect.”

The claims supplied by the inventors are:

“What is claimed is:

“1. A method comprising: receiving, via a network, account data including information regarding currency outlays made by a first sample population; generating, by a computing device, a plurality of behavior patterns based on currency outlay patterns extracted from the account data and age groups for the first sample population; receiving, by the computing device, credit score data for the first sample population; formulating, by the computing device, a model for predicting a credit score change, the model including variables corresponding to each of the plurality of behavior patterns and a likely credit score affect; storing the model on a data storage device; receiving, by the computing device, account data of a subject, extracting, by the computing device, behavior patterns of the subject from the account data of the subject, matching the subject’s extracted behavior patterns with select behavior patterns included in the model that are likely to improve a credit score of the subject based on following a behavior of the select behavior patterns, transmitting, to a user device, the select behavior patterns as behavior recommendations for the subject and the likely credit score affect, transmitting, to the user device, a message identifying at least one of the plurality of behavior patterns and the likely credit score affect, wherein the at least one of the plurality of behavior patterns include: a behavior a user of the user device has repeated on a regular basis in the past and is likely to repeat in the near future, and behaviors of friends of the user of the user device; implementing the at least one of the plurality of behavior patterns; receiving updated credit score data for the first sample population; processing each credit scored included in the updated credit score data by: when an updated credit score of an individual is greater than the individual’s previous credit score, grading the model with a positive value, and when the updated credit score of the individual is less than the individual’s prior credit score, grading at least one of the behavior patterns with a negative value; and removing a behavior pattern from the model when an accumulation of negative values exceeds a threshold.

“2. The method of claim 1, wherein the information regarding currency outlays includes information regarding payments made on credit accounts by the first sample population and spending data including information regarding purchases made.

“3. The method of claim 2, wherein the plurality of behavior patterns includes a plurality of payment and spending behaviors that are defined by at least one payment characteristic of the payments made on the credit accounts and at least one spending characteristic of the purchases made, respectively.

“4. The method of claim 3, wherein the at least one payment characteristic includes at least one of an on-time payment, a payment in full, and a minimum payment.

“5. The method of claim 3, wherein the at least one spending characteristic includes at least one of a consumer purchase and a regularly occurring purchase.

“6. The method of claim 3, wherein generating the plurality of behavior patterns includes defining permutations of the plurality of payment and spending behaviors.

“7. The method of claim 1, wherein the credit score data corresponds to the information regarding currency outlays.

“8. The method of claim 1, wherein the model is formulated according to at least one of a statistical analysis, a Monte Carlo simulation, a single variable regression analysis, and a multivariable regression analysis.

“9. The method of claim 1, further comprising validating the model against account and credit score data of a second sample population.

“10. A system comprising: a network interface device; a processor; and a memory that store instructions that, when executed by the processor, cause the processor to perform operations comprising: receiving, via the network interface device, account data including information regarding currency outlays made by a first sample population, generating a plurality of behavior patterns based on currency outlay patterns extracted from the account data and age groups for the first sample population, receiving credit score data for the first sample population, formulating a model for predicting a credit score change, the model including variables corresponding to each of the plurality of behavior patterns and a likely credit score affect, storing, to the memory, the model, receiving account data of a subject, extracting behavior patterns of the subject from the account data of the subject, matching the subject’s extracted behavior patterns with select behavior patterns included in the model that are likely to improve a credit score of the subject based on following a behavior of the select behavior patterns, transmitting, to a user device, the select behavior patterns as behavior recommendations for the subject and the likely credit score affect, wherein at least one of the select behavior patterns include: a behavior a user of the user device has repeated on a regular basis in the past and is likely to repeat in the near future, and behaviors of friends of the user of the user device, receiving an indication that the user implemented the at least one of the behavior recommendations, receiving updated credit score data for the first sample population; processing each credit scored included in the updated credit score data by: when an updated credit score of an individual is greater than the individual’s previous credit score, grading the model with a positive value, and when the updated credit score of the individual is less than the individual’s prior credit score, grading at least one of the behavior patterns with a negative value; and removing a behavior pattern from the model when an accumulation of negative values exceeds a threshold.

“11. The system of claim 10, wherein the information regarding currency outlays includes information regarding payments made on credit accounts by the first sample population and spending data including information regarding purchases made.

“12. The system of claim 11, wherein the plurality behavior patterns include s a plurality of payment and spending behaviors that are defined by at least one payment characteristic of the payments made on the credit accounts and at least one spending characteristic of the purchases made, respectively.

“13. The system of claim 12, wherein the at least one payment characteristic includes at least one of an on-time payment, a payment in full, and a minimum payment, wherein the at least one spending characteristic includes at least one of a consumer purchase and a regularly occurring purchase, and wherein generating the plurality of behavior patterns includes defining permutations of the plurality of payment and spending behaviors.

“14. The system of claim 10, wherein the credit score data corresponds to the information regarding currency outlays.”

For additional information on this patent, see: Szollar, Suzan. Extracting Behaviors And Suggesting Behaviors To Achieve A Desired Credit Score. U.S. Patent Number 10,803,517, filed July 31, 2015, and published online on October 26, 2020. Patent URL: http://patft.uspto.gov/netacgi/nph-Parser?Sect1=PTO1&Sect2=HITOFF&d=PALL&p=1&u=%2Fnetahtml%2FPTO%2Fsrchnum.htm&r=1&f=G&l=50&s1=10,803,517.PN.&OS=PN/10,803,517RS=PN/10,803,517

(Our reports deliver fact-based news of research and discoveries from around the world.)