SYSTEM AND METHOD OF CLASSIFYING FINANCIAL TRANSACTIONS BY USAGE PATTERNS OF A USER

• US 20130325681A1
• Filed: 05/29/2013
• Published: 12/05/2013
• Est. Priority Date: 01/21/2009
• Status: Abandoned Application

• Current Assignee: Truaxis, Inc. (MasterCard Incorporated)
• Original Assignee: Truaxis, Inc. (MasterCard Incorporated)
• Inventors: Kulkarni, Nilesh Vijay, Kothari, Samir, Somashekar, Manjunath Sulibele, Shah, Akshit Mukesh
• Application Number:
  US13/904,593
• Publication Number:
  US 20130325681A1
• Time in Patent Office: Days
• US Class Current: 705/35
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data
• CPC Class Codes: G06Q 40/00 Finance; Insurance; Tax strategies; Processing of corporate or income taxes
• CPC Class Codes: H04M 15/00 Arrangements for metering, time-control or time indication ; Metering, charging or billing arrangements for voice wireline or wireless communications, e.g. VoIP
• CPC Class Codes: H04M 15/44 Augmented, consolidated or itemized billing statement or bill presentation
• CPC Class Codes: H04M 15/58 based on statistics of usage or network monitoring
• CPC Class Codes: H04M 15/745 Customizing according to wishes of subscriber, e.g. friends or family
• CPC Class Codes: H04M 15/80 Rating or billing plans; Tariff determination aspects
• CPC Class Codes: H04M 15/8011 using class of subscriber
• CPC Class Codes: H04M 15/8044 Least cost routing
• CPC Class Codes: H04M 15/805 Bidding
• CPC Class Codes: H04M 15/8083 involving reduced rates or discounts, e.g. time-of-day reductions or volume discounts
• CPC Class Codes: H04M 15/83 Notification aspects
• CPC Class Codes: H04M 15/84 Types of notifications
• CPC Class Codes: H04M 15/85 characterised by the type of condition triggering a notification
• CPC Class Codes: H04M 15/851 Determined tariff
• CPC Class Codes: H04M 2215/0104 Augmented, consolidated or itemised billing statement, e.g. additional billing information, bill presentation, layout, format, e-mail, fax, printout, itemised bill per service or per account, cumulative billing, consolidated billing
• CPC Class Codes: H04M 2215/0108 Customization according to wishes of subscriber, e.g. customer preferences, friends and family, selecting services or billing options, Personal Communication Systems [PCS]
• CPC Class Codes: H04M 2215/018 On-line real-time billing, able to see billing information while in communication, e.g. via the internet
• CPC Class Codes: H04M 2215/0184 involving reduced rates or discounts, e.g. time-of-day reductions, volume discounts, cell discounts, group billing, frequent calling destination(s) or user history list
• CPC Class Codes: H04M 2215/0188 Network monitoring; statistics on usage on called/calling number
• CPC Class Codes: H04M 2215/74 : Rating aspects, e.g. rating parameters or tariff determination apects
• CPC Class Codes: H04M 2215/7407 : class of subscriber
• CPC Class Codes: H04M 2215/745 : Least cost routing, e.g. Automatic or manual, call by call or by preselection
• CPC Class Codes: H04M 2215/7457 : Biding
• CPC Class Codes: H04M 2215/81 : Notifying aspects, e.g. notifications or displays to the user
• CPC Class Codes: H04M 2215/8129 : Type of notification
• CPC Class Codes: H04M 2215/815 : Notification when a specific condition, service or event is met

Abstract

Disclosed herein is a method of classifying financial transactions by usage patterns of a user. The method includes analyzing metadata extracted from the information associated with financial transactions in accordance with at least one business rule. Where the analysis includes sequentially analyzing the metadata using a constant-time lookup data structure, a Radix tree, a Lucene tree and fuzzy logic methods, until a unique identifier is found that is associated with the metadata. The metadata with the unique identifier is then added to the constant-time lookup data structure to update the constant-time lookup data structure. The transaction data is then classified based on the unique identifier.

Claims

1. A method of classifying financial transactions, comprising:

gathering transaction data from a user'"'"'s financial account;

extracting metadata from the transaction data in accordance with at least one business rule;

sequentially analyzing the metadata using at least one of a constant-time lookup data structure, a Radix tree, a Lucene tree and a fuzzy logic method until a unique identifier is found that is associated with the metadata;

adding the metadata with the unique identifier to the constant-time lookup data structure; and

classifying the transaction data based on the unique identifier.

2. The method of claim 1, wherein the transaction data comprises at least one of a checking transaction, a credit card transaction, a prepaid card transaction, and a bill pay transaction.

3. The method of claim 1, wherein the metadata comprises at least one of a merchant, a geographic location, a merchant category, a date and a time.

4. The method of claim 1 further comprising:

segregating the transaction data into segregated information.

5. The method of claim 4, wherein the segregated information comprises at least one of a date of a transaction, an amount of a transaction, a merchant and a geographic location.

6. The method of claim 4, wherein preprocessing techniques are used to segregate the transaction data.

7. The method of claim 6, wherein the preprocessing techniques comprise at least one processing rule from the group consisting of text transitions between character types and transitions from letters to numbers or delimiting characters.

8. The method of claim 1, wherein classifying includes organizing financial transactions to identify financially related usage patterns of the user.

9. A method of classifying financial transactions, comprising:

gathering transaction data from a user'"'"'s financial account;

extracting metadata from the transaction data in accordance with at least one business rule;

using a Radix tree to identify a unique identifier associated with the metadata; and

classifying the transaction data based on the unique identifier.

10. The method of claim 9 further comprising:

using a location Radix tree to identify unique geolocation identifiers; and

using a merchant Radix tree to identify unique merchant identifiers.

11. A method of classifying financial transactions, comprising:

gathering transaction data from a user'"'"'s financial account;

extracting metadata from the transaction data in accordance with at least one business rule;

using a Lucene tree to identify a unique identifier associated with the metadata; and

classifying the transaction data based on the unique identifier.

12. The method of claim 11 further comprising:

using a location Lucene tree to identify unique geolocation identifiers; and

using a merchant Lucene tree to identify unique merchant identifiers.

13. The method of claim 11, wherein the associated metadata and unique identifier are used to populate a constant-time lookup data structure.

14. The method of claim 11, wherein a partial match in the Lucene tree between the metadata and the unique identifier is compared to a predetermined threshold and if the threshold is exceeded, the unique identifier is associated with the metadata.

15. The method of claim 11, wherein the unique identifier comprises at least one of a geographical location, a zipcode, a merchant name, a merchant category and a date.

16. A method, comprising:

gathering transaction data from a user'"'"'s financial account;

extracting metadata from the transaction data in accordance with at least one business rule;

using fuzzy logic to identify a unique identifier associated with the metadata; and

classifying the transaction data based on the unique identifier.

17. The method of claim 16, wherein the associated metadata and unique identifier are used to populate a constant-time lookup data structure.

18. The method of claim 16, wherein a partial match in the fuzzy logic between the metadata and the unique identifier is compared to a predetermined threshold and if the threshold is exceeded, the unique identifier is associated with the metadata.

19. The method of claim 16, wherein the unique identifier comprises at least one of a geographical location, a zipcode, a merchant name, a merchant category and a date.