Purchase sequence browser

• US 7,962,368 B2
• Filed: 10/20/2006
• Issued: 06/14/2011
• Est. Priority Date: 06/02/2006
• Status: Active Grant

• Current Assignee: Fair Isaac Corporation
• Original Assignee: Fair Isaac Corporation
• Inventors: Kumar, Shailesh, Rosario, Helen Geraldine E, Thorsen, Megan, Little, Colin E, Joshi, Ashutosh, Tolmanov, Sergei
• Primary Examiner(s): ZURITA, JAMES H
• Application Number:
  US11/551,683
• Publication Number:
  US 20070282699A1
• Time in Patent Office: 1,698 Days
• Field of Search: 705/26, 705/37, 705/26.1, 705/27.1
• US Class Current: 705/26.1
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0601 Electronic shopping [e-shopping]
• CPC Class Codes: G06Q 30/0625 Directed, with specific intent or strategy
• CPC Class Codes: G06Q 30/0633 Lists, e.g. purchase orders, compilation or processing
• CPC Class Codes: G06Q 30/0641 Shopping interfaces
• CPC Class Codes: G06Q 30/0643 Graphical representation of items or shoppers
• CPC Class Codes: G06Q 40/04 Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange

Abstract

The invention provides a purchase sequence browser (PuSB), i.e. a graphical user interface (GUI) that facilitates insight discovery and exploration of product affinities across time, generated by a purchase sequence analysis of a retailer'"'"'s transaction data. A purchase sequence browser allows the user to browse the most significant product phrases discovered by an exhaustive search of the product affinities across time; explore the retail grammar to create both forward and backward phrase trees or alternate purchase paths starting from, or ending in, a product; generate consistent purchase sequences given some constraints on the products and their order; and profile the value of a product across time with regard to other products fixed in time.

Claims

1. A method for browsing a purchase sequence, the method being implemented by one or more data processors and comprising the steps of:

generating, by at least one data processor, a purchase sequence analysis of a retailer'"'"'s transaction data relating to purchases by a plurality of consumers;

providing, by at least one data processor, a graphical user interface that uses said purchase sequence analysis to facilitate insight discovery and exploration of product affinities across time;

providing a purchase sequence browser, said purchase sequence browser, in conjunction with said graphical user interface, further performing at least one any of the steps of;

allowing a user to browse most significant product phrases discovered by an exhaustive search of product affinities across time;

exploring a retail grammar to create both forward and backward phrase trees or alternate purchase paths starting from, or ending in, a product;

generating consistent purchase sequences given constraints on products and their order; and

profiling a value of a product across time with regard to other products fixed in time.

2. The method as in claim 1, wherein the graphical user interface renders

a tree diagram showing an active product at all but a terminal time stamp;

wherein, by default, top products are active in first and second columns;

wherein, when a user selects any of the displayed products to be active, a list of products is populated in a next column based on all active products in the past; and

wherein default active products are kept as a first product in a new list.

3. The method as in claim 1, wherein the graphical user interface enables backward exploration of an active product.

4. The method as in claim 1, wherein the graphical user interface enables keeping of a time lag or not for an active product;

wherein, by default, a time-lag is one time-unit; and

wherein said user can ignore a particular time-slot.

5. The method as in claim 1, further comprising:

using consistencies to grow forward using a forward aggregate scoring function.

6. The method as in claim 1, further comprising:

using consistencies to grow backward using a backward aggregate scoring function according to the invention.

7. The method of claim 1, wherein the providing comprises:

providing one or more panels, the panels comprising at least one of;

a product panel;

a sequence panel; and

a property panel.

8. The method of claim 1 further comprising:

providing a browser panel for allowing a user to browse pre-created high consistency product phrases;

providing an explorer panel for allowing a user to grow/shrink purchase sequences manually;

providing a generator panel for automatically generating phrases from a product set;

providing a profiler panel for showing time profiles of products for a given sequence; and

providing a favorites panel for collecting sequences that a user adds to favorites.

9. The method as in claim 8, wherein the browser panel comprises:

a drop down list from which a user selects a product;

wherein all pre-created phrases that contain the selected product are listed in a table.

10. The method as in claim 9, wherein the table comprises the following properties:

Phrase ID=row number in the PHRASE file;

Trigger Product (first product) name;

Length of the phrase;

Duration of the phrase;

Phraseness measure (min/max); and

Ability to add other product properties as in bundles/bridges.

11. The method as in claim 8, wherein the explorer panel comprises:

a drop-down menu that provides options to;

Display Phrase tree;

Explore Phrase FORWARD; and

Explore Phrase BACKWARD.

12. The method as in claim 11, wherein a product is placed either in a top LEFT or top RIGHT corner of said explorer panel, depending on whether the user selected (FORWARD) or (BACKWARD) respectively.

13. The method as in claim 8, wherein the The purchase sequence explorer panel comprises:

a forward phase tree and a backward phase tree, each said phase tree further comprising the following parameters;

Time Scale;

Maximum Length; and

Maximum Branch.

14. The method as in claim 8, wherein the generator panel comprises at least one any of:

a product constraint, wherein a user may select two or more products either from the product panel or from the property panel, or from a sub-graph, neighbor, bundle, or bridge structure, wherein said generator generates product phrases using only these products; and

a set of order constraints, wherein a user specifies an order of certain products, wherein each product is anchored or non-anchored in a particular position, wherein an anchored product cannot change its position and all products above/below it must remain there in their ordering;

wherein a sorted list of product phrases that satisfy either or both constraints is generated.

15. The method as in claim 8, wherein the profiler panel enables:

profiling any of consistency and phraseness of one or more products, wherein said profile is generated against at least one any of;

a given phrase with an entire phrase blanket, wherein all products in a phrase affect the profile;

a given phrase with a subset phrase blanket, wherein a chosen few products in a phrase affect the profile; and

a given phrase with a maximal phrase blanket, wherein each profile value is maximized across available phrase blankets.

16. The method as in claim 8, wherein the profiler panel enables:

choosing measure to plot in a graph to show consistency of phraseness.

17. The method as in claim 16, wherein the profiler panel enables:

choosing a phrase blanket to use.

18. A method for browsing a purchase sequence, the method being implemented by one or more data processors and comprising:

generating, by at least one data processor, a purchase sequence analysis of a retailer'"'"'s transaction data relating to purchases by a plurality of consumers;

providing, by at least one data processor, a graphical user interface that uses the purchase sequence analysis to facilitate insight discovery and exploration of product affinities across time;

wherein the graphical user interface enables;

allowing a user to browse most significant product phrases discovered by an search of product affinities across time;

exploring a retail grammar to create both forward and backward phrase trees or alternate purchase paths starting from, or ending in, a product;

generating consistent purchase sequences given constraints on products and their order; and

profiling a value of a product across time with regard to other products fixed in time.