PREDICTIVE CONVERSION SYSTEMS AND METHODS

• US 20120143861A1
• Filed: 01/24/2012
• Published: 06/07/2012
• Est. Priority Date: 12/12/2007
• Status: Active Grant

• Current Assignee: Vast.com, Inc. (Vroom, Inc.)
• Original Assignee: Vast.com, Inc. (Vroom, Inc.)
• Inventors: Sethi, Komal Singh, Tatarevic, Milos Milinko, Bradic, Aleksandr Milutin, Laws, Kevin Allen
• Granted Patent: US 8,375,037 B2
• Time in Patent Office: Days
• US Class Current: 707/731
• CPC Class Codes: G06F 16/244 Grouping and aggregation
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/2462 Approximate or statistical queries
• CPC Class Codes: G06F 16/2465 Query processing support for facilitating data mining operations in structured databases
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/907 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/9538 Presentation of query results
• CPC Class Codes: G06Q 10/087 Inventory or stock management, e.g. order filling, procurement or balancing against orders
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

In one embodiment, a system and method of predicting sale transaction conversion rate of an item operates through a search of information in response to a query over a network. The system and method can includes discovering available information of the item of interest, extracting certain of the available information of the item, analyzing the certain information by comparing the information to other item information, weighting the information for the item in comparison to other items of the category, calculating a predictive score for the item of interest, and presenting the information of the item of interest ranked according to the predictive score as compared to other items of the category.

Claims

1. A computer system for generating and applying a formula for calculating an expected conversion rate, the computer system comprising:

an electronic memory storage configured to store modules;

a computer processor configured to execute the modules comprising at least;

a data access module configured to access from a data repository stated metadata and derived metadata elements, wherein the stated metadata elements and the derived metadata elements are for a plurality of products that led to prior user conversions,

a conversions module configured to determine the relevance of each stated metadata element and each derived metadata element in deriving expected conversion rates, wherein the determination is based on the use of a linear or logistic regression analysis,

a formula generation module configured to generate on a periodic basis a formula based on the determination, wherein the formula takes into account a plurality of stated metadata elements and derived metadata elements that have been determined to be statistically relevant to expected conversion rates, and

a formula application module configured to apply the formula to a plurality of products in an inventory database to assign a predicted conversion rate for each of the plurality of products in the inventory database.

2. The computer system of claim 1, further comprising an analytics module configured to receive a request for a listing of available products in a specific product category or product identification over a network.

3. The computer system of claim 2, further comprising a ranking and recommendation module configured to prioritize the listing of available products based on the assigned predicted conversion rates, and configured to transmit the listing of available products over the network.

4. The computer system of claim 3, wherein the request is received from a computing device from the group comprising of a desktop, a laptop, a personal data assistant, or a data-enabled phone.

5. The computer system of claim 1, wherein the linear or logistic regression analysis is generated based on an analysis of historical conversion rates for at least one product in the plurality of products.

6. The computer system of claim 5, wherein the analysis of historical conversion rates comprises a probability that a user clicks on a particular product based on an analysis of historical user behavior.

7. The computer system of claim 1, wherein stated metadata comprises attributes of a product that are obtained from a product description provided by advertisers or suppliers of the plurality of products in the inventory database.

8. The computer system of claim 1, wherein derived metadata comprises attributes of a product that are provided by a third party source and that are not stated in a product description provided by advertisers or suppliers of the plurality or products in the inventory database.

9. The computer system of claim 1, wherein the predicted conversion rate relates to lead generation.

10. The computer system of claim 1, wherein the predicted conversion rate relates to generating higher advertising revenue.

11. The computer system of claim 1, wherein the formula takes into account a weighting factor for each of the plurality of stated and derived metadata elements that have been determined to be statistically relevant to expected conversion rates.

12. The computer system of claim 11, wherein the conversions module is further configured to increase a weighting factor for each of the plurality of stated and derived metadata elements that lead to a greater number of conversions.