Methods and systems for implementing automated bidding models

Patent metadata

Field	Value
Publication number	US-11449903-B2
Application number	US-202017064242-A
Country	US
Kind code	B2
Filing date	Oct 6, 2020
Priority date	Sep 4, 2019
Publication date	Sep 20, 2022
Grant date	Sep 20, 2022

Abstract

A system may include an aggregate model comprising a plurality of modules, a monitoring dashboard in communication with the aggregate model, and a search-marketing campaign manager in communication with the aggregate model, the monitoring dashboard, and a search engine entity. Additionally, the system may include a bidding interface in communication with the aggregate model and a search engine entity and/or a monitoring dashboard configured to generate model adjustment data. The search-marketing campaign manager may be configured to determine trend data, measured marketing indicators, or both, from one or more of marketing data or historical data.

First claim

What is claimed is:

1. A computer-implemented method for determining a bid cost for a bid, the method comprising:
using an aggregate model to predict a functional relationship between the bid cost of the bid and a net present value of the bid, wherein the aggregate model includes a plurality of modules;
generating model adjustment data that includes information configured to cause the aggregate model to adjust one or more of the plurality of modules independently of each other;
transmitting the model adjustment data to the aggregate model so that one or more of the plurality of modules is adjusted independently of other modules in the aggregate model;
determining the bid cost for the bid using the aggregate model adjusted by the model adjustment data; and
transmitting the bid with the determined bid cost to at least one search engine entity.

2. The method of claim 1 , wherein the method is executed by a system that includes:
a processor;
a communication component operatively connected to the processor, and configured to enable communication between the system and the at least one search engine entity, the at least one search engine entity being remote from the system; and
a memory operatively connected to the processor, and storing data and instructions executable by the processor.

3. The method of claim 2 , wherein:
the data stored in the memory includes a database including one or more of historical data and marketing data related to one or more keywords; and
the method further comprises determining one or more of trend data or at least one measured marketing indicator based on the one or more of the marketing data or historical data.

4. The method of claim 3 , wherein the aggregate model is configured to determine the functional relationship based on the one or more of the marketing data or the trend data.

5. The method of claim 1 , wherein the aggregate model is configured to increase net present value of a bid related to a target keyword.

6. The method of claim 5 , wherein at least one module of the plurality of modules of the aggregate model is related to a keyword other than the target keyword.

7. The method of claim 1 , wherein each module of the plurality of modules of the aggregate model is based on one or more of eligible impressions per search, clicks per eligible impression, applications per click, loans per application, present value (PV) per loan, or cost per click.

8. The method of claim 7 , wherein the aggregate model is configured to predict the net present value (NPV) as a function of bid cost (Cost) according to:

NPV
=

Total
⁢

⁢
Search
×

Eligible
⁢

⁢
Impressions

Total
⁢

⁢
Search

×

Clicks

Eligible
⁢

⁢
Impressions

×

(

Applications
Clicks

×

Loans
Applications

×

PV
Loan

-

Cost
Click

)

.

9. The method of claim 1 , wherein the aggregate model is configured to determine, based on the functional relationship, a plurality of net present values for the bid corresponding to a range of bid costs, and to select a particular bid cost from amongst the range of bid costs corresponding to a highest of the net present values for the particular bid to be transmitted to the at least one search engine entity.

10. A computer-implemented method for determining a bid cost for a bid, the method executed by a processor of a system based on instructions stored in a memory of the system, the method comprising:
causing a monitoring dashboard executed by the processor to generate model adjustment data and transmit the model adjustment data to an aggregate model that is stored in the memory and that includes a plurality of modules, the model adjustment data including information that causes the aggregate model to adjust one or more of the plurality of modules independently of each other;
causing the aggregate model to predict a functional relationship between a bid cost of a bid and a net present value of the bid; and
causing a bidding interface executed by the processor and in communication with the aggregate model to transmit, via a communication component operatively connected to the processor, a particular bid to at least one search engine entity remote from the system.

11. The method of claim 10 , further comprising:
causing a search-marketing campaign manager executed by the processor and in communication with the aggregate model and the monitoring dashboard to determine one or more of trend data or measured marketing indicators based on one or more of marketing data or historical data stored in the memory.

12. The method of claim 11 , further comprising:
causing the search-marketing campaign manager to transmit the trend data to the aggregate model, transmit the measured marketing indicators to the monitoring dashboard, or both.

13. The method of claim 11 , further comprising:
causing the search-marketing campaign manager to transmit the measured marketing indicators to the monitoring dashboard, wherein the model adjustment data is generated based on the measured marketing indicators.

14. The method of claim 10 , wherein the aggregate model is configured to increase net present value of a bid related to a target keyword.

15. The method of claim 14 , wherein at least one module of the plurality of modules of the aggregate model is related to a keyword other than the target keyword.

16. The method of claim 10 , wherein each module of the plurality of modules of the aggregate model is based on one or more of eligible impressions per search, clicks per eligible impression, applications per click, loans per application, present value (PV) per loan, or cost per click.

17. The method of claim 16 , wherein the aggregate model is configured to predict the net present value (NPV) as a function of bid cost (Cost) according to:

NPV
=

Total

Assignees

• Capital One Services Llc

Inventors

• Manion Patrick
• Truong Edmond
• Sun Meng
• Shen Jie

Classifications

• G06Q10/067

  Enterprise or organisation modelling · CPC title

• G06Q30/0256

  User search · CPC title

• G06Q30/0275 Primary

  Auctions · CPC title