System and method for generating a finance attribute from tradeline data

• US 9,563,916 B1
• Filed: 11/26/2013
• Issued: 02/07/2017
• Est. Priority Date: 10/05/2006
• Status: Active Grant

• Current Assignee: Experian Information Solutions Incorporated (Experian plc)
• Original Assignee: Experian Information Solutions Incorporated (Experian plc)
• Inventors: Torrez, Luz M., Kornegay, Adam Thomas
• Primary Examiner(s): Chang, Edward
• Application Number:
  US14/091,232
• Time in Patent Office: 1,169 Days
• Field of Search: 705/38, 705/35
• US Class Current: 1/1
• CPC Class Codes: G06F 16/254 Extract, transform and load [ETL] procedures, e.g. ETL data flows in data warehouses
• CPC Class Codes: G06Q 10/04 Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" market predictions or forecasting for commercial activities G06Q30/0202
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
• CPC Class Codes: G06Q 40/03 Credit; Loans; Processing thereof

Abstract

Embodiments of a system and method are described for generating a finance attribute. In one embodiment, the systems and methods retrieve raw tradeline data from a plurality of credit bureaus, retrieve industry code data related to each of the plurality of credit bureaus, determine one or more tradeline leveling characteristics that meet at least one pre-determined threshold, and generate a finance attribute using the selected leveling characteristics.

Claims

1. A computer-implemented method for generating an attribute from raw tradeline data stored in different formats by a plurality of credit data sources, the method comprising:

providing a computer system comprising a plurality of computing devices, the computer system in electronic communication with a network and comprising;

at least a first internal consumer credit data warehouse storing raw tradeline data for at least a large plurality of consumers, the raw tradeline data categorized using a first set of tradeline category codes to denote each of a variety of first tradeline categories;

a network interface configured to electronically communicate via the network with a second external consumer credit data warehouse storing raw tradeline data for at least the large plurality of consumers, the raw tradeline data categorized using a second set of tradeline category codes to denote each of a variety of second tradeline categories,

wherein the first set of tradeline category codes and the second set of tradeline category codes each include one or two-letter industry codes and wherein the first set of tradeline category codes have at least a degree of commonality with the second set of tradeline category codes, but at least a subset of the second set of tradeline category codes is different from the first set of tradeline category codes, the second external consumer credit data warehouse is independent and different from the first internal consumer credit data warehouse, and the first internal consumer credit data warehouse and the second external consumer credit data warehouse electronically store at least a portion of the raw tradeline data in different formats, wherein the different formats comprise one or more differences in the first set of tradeline category codes and the second set of tradeline category codes,

the network interface further configured to electronically communicate with a plurality of client user devices to access raw tradeline data of the first internal consumer credit data warehouse and the second external consumer credit data warehouse, the plurality of client user devices associated with financial service providers; and

an attribute leveling server generating leveled attributes and electronically delivering the leveled attributes to the plurality of client user devices via the network interface to allow the plurality of client user devices to receive normalized tradeline data, the attribute leveling server comprising one or more processors which when programmed carry out instructions including;

accessing, via the one or more processors, first raw tradeline data from the first internal consumer credit data warehouse corresponding to a first time period;

accessing, via the one or more processors, second raw tradeline data from the second external consumer credit data warehouse corresponding to the first time period;

accessing, via the one or more processors respective first tradeline category codes associated with the first raw tradeline data and respective second tradeline category codes associated with the second raw tradeline data;

automatically determining, via the one or more processors, one or more electronic tradeline characteristics associated with the respective first tradeline category codes associated with the first raw tradeline data and the respective second tradeline category codes associated with the second raw tradeline data to select as leveling characteristics for the first raw tradeline data and the second raw tradeline data, wherein the leveling characteristics are configured to yield substantially consistent tradeline data for at least the first time period when applied to raw tradeline data from the first internal consumer credit data warehouse and raw tradeline data from the second external consumer credit data warehouse, wherein automatically determining one or more electronic tradeline characteristics comprises applying a software module comprising an iterative mathematical or logical operation to the first raw tradeline data and the second raw tradeline data, wherein the mathematical or logical operation comprises;

selecting a first set of the first tradeline category codes and a second set of the second tradeline category codes wherein the first set and the second set have a first degree of commonality and are potential leveling characteristics;

accessing first raw tradeline data associated with the first set and second raw tradeline data associated with the second set;

measuring a correlation among the retrieved first raw tradeline data associated with the first set and second raw tradeline data associated with the second set

determining whether the correlation meets at least one predefined threshold;

if the correlation does not meet the at least one predefined threshold,

 

updating the first set or the second set to include different first tradeline category codes or different second tradeline category codes than were previously in the first set or the second set, wherein the updated first set or second set have an equal or lesser degree of commonality than before; and

 

iteratively performing the accessing, measuring, and determining; and

if the correlation meets the at least one predefined threshold,

generating, via the one or more processors, a leveled attribute for the first raw tradeline data and the second raw tradeline data using the first set and the second set; and

generating, via the one or more processors, an electronic attribute data structure which stores an electronic indication of the leveled attribute.

2. The computer-implemented method of claim 1, wherein the first time period is measured in months.

3. The computer implemented method of claim 1, wherein automatically determining, via the one or more processors, one or more electronic tradeline characteristics to select as leveling characteristics further comprises:

designating, based on iterations of the mathematical or logical operation, leveling characteristics;

using the first raw tradeline data and the second raw tradeline data to generate test tradeline data using the leveling characteristics;

adjusting the leveling characteristics if the difference fails to meet the at least one pre-defined threshold; and

repeating said using and adjusting until the leveling characteristics generate a difference that meets the at least one pre-defined threshold.

4. The computer implemented method of claim 3 further comprising excluding extraneous raw tradeline data from the leveled tradeline data.

5. The computer implemented method of claim 3 further comprising:

measuring a difference between a non-leveled attribute and the leveled attribute; and

determining whether the difference meets at least one pre-defined threshold.

6. The computer implemented method of claim 1, wherein the second external consumer credit data warehouse is associated with a credit bureau.

7. The computer implemented method of claim 1, wherein the tradeline category codes include industry identifiers.

8. A computing system comprising:

at least a first internal consumer credit data warehouse storing raw tradeline data for at least a large plurality of consumers, the raw tradeline data categorized using a first set of tradeline category codes to denote each of a variety of first tradeline categories;

a network interface configured to electronically communicate via a network with a second external consumer credit data warehouse storing raw tradeline data for at least the large plurality of consumers, the raw tradeline data categorized using a second set of tradeline category codes to denote each of a variety of second tradeline categories,

wherein the first set of tradeline category codes and the second set of tradeline category codes each include one or two-letter industry codes and wherein the first set of tradeline category codes have at least a degree of commonality with the second set of tradeline category codes, but at least a subset of the second set of tradeline category codes is different from the first set of tradeline category codes, the second external consumer credit data warehouse is independent and different from the first internal consumer credit data warehouse, and the first internal consumer credit data warehouse and the second external consumer credit data warehouse electronically store at least a portion of the raw tradeline data in different formats, wherein the different formats comprise one or more differences in the first set of tradeline category codes and the second set of tradeline category codes,

the network interface further configured to electronically communicate with a plurality of client user devices to access raw tradeline data of the first internal consumer credit data warehouse and the second external consumer credit data warehouse, the plurality of client user devices associated with financial service providers;

an attribute leveling server generating leveled attributes and electronically delivering the leveled attributes to the plurality of client user devices via the network interface to allow the plurality of client user devices to receive normalized tradeline data, the attribute leveling server comprising one or more processors and a communications memory device comprising instructions configured, via the one or more processors, to;

access first raw tradeline data from the first internal consumer credit data warehouse corresponding to a first time period;

access second raw tradeline data from the second external consumer credit data warehouse corresponding to the first time period; and

access respective first tradeline category codes associated with the first raw tradeline data and respective second tradeline category codes associated with the second raw tradeline data;

automatically determine one or more electronic tradeline characteristics associated with the respective first tradeline category codes associated with the first raw tradeline data and the respective second tradeline category codes associated with the second raw tradeline data to select as leveling characteristics for the first raw tradeline data and the second raw tradeline data, wherein the leveling characteristics are configured to yield substantially consistent tradeline data for at least the first time period when applied to raw tradeline data from the first internal consumer credit data warehouse and raw tradeline data from the second external consumer credit data warehouse, wherein automatically determining one or more electronic tradeline characteristics comprises applying a software module comprising an iterative mathematical or logical operation to the first raw tradeline data and the second raw tradeline data, wherein the mathematical or logical operation comprises;

selecting a first set of the first tradeline category codes and a second set of the second tradeline category codes wherein the first set and the second set have a first degree of commonality and are potential leveling characteristics;

accessing first raw tradeline data associated with the first set and second raw tradeline data associated with the second set;

measuring a correlation among the retrieved first raw tradeline data associated with the first set and second raw tradeline data associated with the second set

determining whether the correlation meets at least one predefined threshold;

if the correlation does not meet the at least one predefined threshold,

 

updating the first set or the second set to include different first tradeline category codes or different second tradeline category codes than were previously in the first set or the second set, wherein the updated first set or second set have an equal or lesser degree of commonality than before; and

 

iteratively performing the accessing, measuring, and determining; and

if the correlation meets the at least one predefined threshold,

generate a leveled attribute for the first raw tradeline data and the second raw tradeline data using the first set and the second set; and

generate an electronic attribute data structure which stores an electronic indication of the leveled attribute.

9. The computing system of claim 8 wherein the communications memory device further comprises instructions configured to automatically determine one or more electronic tradeline characteristics to select as leveling characteristics by:

designating, based on iterations of the mathematical or logical operation, leveling characteristics, wherein the lowest common denominators comprise a minimum set of overlapping industry codes;

using the first raw tradeline data and the second raw tradeline data to generate leveled tradeline data using the leveling characteristics;

adjusting the leveling characteristics if the difference fails to meet the at least one pre-defined threshold; and

repeating said using and adjusting until the leveling characteristics generate a difference that meets the at least one pre-defined threshold.

10. The computing system of claim 8, wherein the first and second raw tradeline data each comprises revolving tradelines.

11. The computing system of claim 8, wherein the first and second raw tradeline data each comprises installment tradelines.

12. The computing system of claim 8, wherein the first and second raw tradeline data each comprises education loan tradelines.

13. The computing system of claim 8, wherein the first and second raw tradeline data each comprises auto loan tradelines.

14. The computing system of claim 8, wherein the leveled attribute comprises a finance attribute.

15. Non-transitory, computer-readable storage media storing computer-executable instructions that, when executed by a computer system comprising one or more processors, configure the computer system to perform the following operations comprising:

storing raw tradeline data for at least a large plurality of consumers in a first internal consumer credit data warehouse, the raw tradeline data categorized using a first set of tradeline category codes to denote each of a variety of first tradeline categories;

electronically communicating via a network with a second external consumer credit data warehouse storing raw tradeline data for at least the large plurality of consumers, the raw tradeline data categorized using a second set of tradeline category codes to denote each of a variety of second tradeline categories,

wherein the first set of tradeline category codes and the second set of tradeline category codes each include one or two-letter industry codes and wherein the first set of tradeline category codes have at least a degree of commonality with the second set of tradeline category codes, but at least a subset of the second set of tradeline category codes is different from the first set of tradeline category codes, the second external consumer credit data warehouse is independent and different from the first internal consumer credit data warehouse, and the first internal consumer credit data warehouse and the second external consumer credit data warehouse electronically store at least a portion of the raw tradeline data in different formats, wherein the different formats comprise one or more differences in the first set of tradeline category codes and the second set of tradeline category codes,

electronically communicating with a plurality of client user devices to access raw tradeline data of the first internal consumer credit data warehouse and the second external consumer credit data warehouse, the plurality of client user devices associated with financial service providers;

generating leveled attributes;

electronically delivering the leveled attributes to the plurality of client user devices via the network to allow the plurality of client user devices to receive normalized data, the attribute leveling server performing operations;

accessing first raw tradeline data from the first internal consumer credit data warehouse, the first raw tradeline data corresponding to a first time period;

accessing second raw tradeline data from the second external consumer credit data warehouse, the second raw tradeline data corresponding to the first time period;

accessing respective first tradeline category codes associated with the first raw tradeline data and respective second tradeline category codes associated with the second raw tradeline data;

automatically determining one or more electronic tradeline characteristics associated with the respective tradeline category codes associated with the first raw tradeline data and the respective second tradeline category codes associated with the second raw tradeline data to select as leveling characteristics for the first raw tradeline data and the second raw tradeline data, wherein the leveling characteristics are configured to yield substantially consistent tradeline data for at least the first time period when applied to raw tradeline data from the first internal consumer credit data warehouse and raw tradeline data from the second external consumer credit data warehouse, wherein automatically determining one or more electronic tradeline characteristics comprises applying a software module comprising an iterative mathematical or logical operation to the first raw tradeline data and the second raw tradeline data, wherein the mathematical or logical operation comprises;

selecting a first set of the first tradeline category codes and a second set of the second tradeline category codes wherein the first set and the second set have a first degree of commonality and are potential leveling characteristics;

accessing first raw tradeline data associated with the first set and second raw tradeline data associated with the second set;

measuring a correlation among the retrieved first raw tradeline data associated with the first set and second raw tradeline data associated with the second set

determining whether the correlation meets at least one predefined threshold;

if the correlation does not meet the at least one predefined threshold,

updating the first set or the second set to include different first tradeline category codes or different second tradeline category codes than were previously in the first set or the second set, wherein the updated first set or second set have an equal or lesser degree of commonality than before; and

iteratively performing the accessing, measuring, and determining; and

if the correlation meets the at least one predefined threshold,

generating a leveled attribute for the first raw tradeline data and the second raw tradeline data using the first set and the second set; and

generating an electronic attribute data structure which stores an electronic indication of the leveled attribute.

16. The non-transitory, computer-readable storage media of claim 15, wherein the first time period is measured in months.

17. The non-transitory, computer-readable storage media of claim 15, wherein automatically determining one or more electronic tradeline characteristics to select as leveling characteristics further comprises:

designating leveling characteristics based on iterations of the mathematical or logical operation;

using the first raw tradeline data and the second raw tradeline data to generate leveled tradeline data using the leveling characteristics;

adjusting the leveling characteristics if the difference fails to meet the at least one pre-defined threshold; and

repeating said using and adjusting until the leveling characteristics generate a difference that meets the at least one pre-defined threshold.

18. The non-transitory, computer-readable storage media of claim 17 further comprising excluding extraneous raw tradeline data from the leveled tradeline data.

19. The non-transitory, computer-readable storage media of claim 17 further comprising:

measuring a difference between a non-leveled attribute and the leveled attribute; and

determining whether the difference meets at least one pre-defined threshold.

20. The non-transitory, computer-readable storage media of claim 15, wherein the tradeline category codes include industry identifiers.