Patent Application
20100094673
1. Technical Field
This disclosure relates to methods and systems supporting keyword advertising associated with Internet search engine usage and keyword query submittal by a user. More particularly, the present disclosure relates to automated bidding for search keywords.
2. Related Art
An increasingly popular way of delivering Internet advertisements is to tie the advertisement to search query results triggered by the entry of particular keywords (e.g. search queries) by a user. In order to target advertising accurately, advertisers or vendors pay to have their advertisements presented in response to certain kinds of queries—that is, their advertisements are presented when particular keyword combinations are supplied by the user of the search engine.
For example, when a user searches for “baseball cards,” using a search engine such as Google or other well-known search engines, in addition to the usual query results, the user can also be shown a number of sponsored results. These can be paid advertisements for businesses, generally offering related goods and/or services. In this example, the advertisements may therefore be directed to such things as baseball card vendors, collectibles shops, sports memorabilia, or even sporting goods or event tickets. Of course, the advertisements may be directed to seemingly less related subject matter. While the presentation varies somewhat between search engines, these sponsored results are usually shown a few lines above, or on the right hand margin of the regular results. Although, the sponsored results may also be placed anywhere in conjunction with the regular results.
Keyword advertising is growing as other types of web advertising are generally declining. It is believed there are at least several features that contribute to its success. First, sponsored results are piggybacked on regular results, so they are delivered in connection with a valuable, seemingly objective, service to the user. By contrast, search engines that are built primarily on sponsored results have not been as popular. Second, the precision of the targeting of the advertising means the user is more likely to find the advertisements useful, and consequently can perceive the advertisements as more of a part of the service than as an unwanted intrusion. Unlike banners and pop-up advertisements, which are routinely ignored or dismissed, users appear more likely to click through these sponsored results (e.g., keyword advertisements). Third, the targeting is based entirely on the current query, and not on demographic data developed over longer periods of time. This kind of targeting is timelier and more palatable to users with privacy concerns. Fourth, these advertisements reach users when they are searching, and therefore when they are more open to visiting new web sites.
Companies, such as Google of Mountain View, Calif., which offers a search engine and Overture of Pasadena, Calif. (now Yahoo Search), which aggregates advertising for search engines as well as offering its own search engine, use an auction mechanism combined with a pay-per-click (PPC) pricing strategy to sell advertising. This model is appealing in its simplicity. Advertisers bid in auctions for placement of their advertisements in connection with particular keywords or keyword combinations. The amount they bid (e.g., cost-per-click (CPC)) is the amount that they are caning to pay for a click-through on their link. For example, in one PPC pricing strategy, if company A bids $1.10 for the keyword combination “baseball cards”, then its advertisement can be placed above a company bidding $0.95 for the same keyword combination. Only a selected number of bidders' advertisements can be shown. The simplicity of the model makes it easy for an advertiser to understand why an advertisement is shown, and what bid is necessary to have an advertisement shown. It also means that advertisers are charged only for positive click-through responses.
Both Google and Overture offer tools to help users identify additional keywords based on an initial set of keywords. The Overture model supplies keywords that actually contain the keyword (e.g. for bicycle one can get road bicycle, Colonago bicycle, etc.). Google, on the other hand, performs some kind of topic selection, which they claim is based on billions of searches.
Both Google and Overture offer tools to help users manage their bids. Google uses click-through rate and PPC to estimate an expected rate of return which is then used to dynamically rank the advertisements. Overture uses the PPC pricing strategy to rank advertisements, but monitors the click-through rate for significantly under performing advertisements.
Because Google dynamically ranks the advertisements based on click-through and PPC, advertisers cannot control their exact advertisement position with a fixed PPC. To insure a top position, the advertiser must be caning to pay a different price that is determined by their own click through rate as well as the competitors click-though rates and PPC. Overture uses a fixed price model, which insures fixed position for fixed price.
If a set of keywords that have not been selected by any of the advertisers is issued as a search term, Google can attempt to find the best matching selected set of keywords and display its associated advertisements. For example, let's say a user searches on “engagement ring diamond solitaire.” However, there are no advertisers bidding on this search term. The expanded matching feature can then match (based on term, title, and description) selected listings from advertisers that have bid on search terms (e.g. keyword combinations) like “solitaire engagement ring” and “solitaire diamond ring.”
A number of third parties provide services to Overture customers to identify and select keywords and track and rank bids. For example, BidRank, Dynamic Keyword Bid Maximizer, Epic Sky, GoToast, PPC BidTracker, PPC Pro, Send Traffic, and Sure Hits. There are a small number of pay-per-bid systems. For example, Kanoodle is a traditional pay-per-bid system like Overture. Other examples, include Sprinks and FindWhat.
The Sprinks brand system, ContentSprinks™, produces listings that rely on context, as opposed to one-to-one matching with a keyword. The user chooses topics, rather than keywords. The Sprinks web site asserts, “Since context is more important than an exact match, you can put your offer for golf balls in front of customers who are researching and buying golf clubs, and your listing can still be approved, even though it's not an exact match.” This is a pay-per-bid model, like Overture, and has been used by About.com, iVillage.com and Forbes.com. The Sprinks brand system, KeywordSprinks™, is a traditional pay-per-bid model for keywords and phrases.
FindWhat has a BidOptimizer that shows the bids of the top five positions so that a user can set their bid price for a keyword to be at a specific position. It does not continually adjust bids like host and Overture.
In addition, there is a system called Wordtracker for helping users to select keywords. The Wordtracker system at <www.wordtracker.com> provides a set of tools to help users to identify keywords for better placement of advertisements and web pages in search engines, both regular and pay-per-bid. Wordtracker provides related words with occurrence information, misspelled word suggestions based on the number of occurrences of the misspelled words, and tools for keeping track of possible keyword/key phrase candidates. The related words are more than variants. On the web site, an example of related keywords for “golf” includes pga, Ipga, golf courses, tiger woods, golf clubs, sports, jack nicklaus, and titleist, as well as phrases that include the term “golf,” such as golf clubs, golf courses, golf equipment, used golf clubs, golf tips, golf games, and vw.golf. Wordtracker displays the bid prices for a keyword on selected pay-per-bid search engines. It also displays the number of occurrences of search terms by search engine so the keywords can be tuned to each search engine.
Wordtracker can be a useful tool, but it does not automate certain aspects of the advertiser's decision-making, bidding, and placement of advertisements. Currently, an advertiser must participate in every auction of relevant keywords. In the example above, a company offering sporting goods may want its advertisements to be placed with a variety of keywords corresponding to common queries related to sports equipment, training, events, etc. These keywords vary in their relevance to the company's business, in their “yield” of productive click-through visits to the company's web site, and their cost to the company (based on competition in the auctions). The multiplicity of keyword combinations and the multiplicity of considerations for each keyword combination create a number of opportunities for automation support mechanisms for advertisement placement decision making.
In the process of bidding in keyword auctions, advertisers may compete in ways that are mutually detrimental. There may be better joint strategies that are less costly, or involve alternative keywords, but the individual bidders do not easily discover these joint strategies. Even when the individual bidders know good joint strategies, the individual bidders may not have a strong incentive to pursue these strategies without some assurance of cooperation.
If the process of selecting and bidding for keyword combinations for an advertiser was automated or more automated, it likely that less guidance would be required from the advertiser and that advertisements would be placed on more effective keywords. It is also likely that such automation would help maximize return on advertising investment (ROAI), increase the number sponsored keywords, and maximize click-through rates for keyword advertisements.
Several published U.S. patent applications disclose concepts related to bidding for a position of a keyword advertisement in a search results list. For example, U.S. Patent Application Pub. No. U.S. 2005/0144064 A1 discloses a method of generating a bid for an advertiser for placement of an advertisement in association with a search results list, where the search results list is generated in response to a search query. In one embodiment, the method includes: a) associating the at least one keyword with the bid, wherein the search query is associated with the at least one keyword, and b) determining an amount of the bid, associated with the at least one keyword, for placement of the advertisement in association with the search results list generated in response to the search query associated with the at least one keyword. The bid is determined based at least in part on bids by other advertisers in competition with the first advertiser for placement of other advertisements with an expectation that the determined bid may elicit a desired change in the bids by the other advertisers.
U.S. Patent Application Pub. No. U.S. 2005/0144065 A1 discloses a method of coordinating one or more bids for one or more groups of advertisers for placement of at least one advertisement in association with a search results list. The search results list is generated in response to a search query. The method includes: a) collecting information from at least two advertisers in the advertiser group and b) devising a joint strategy for the advertiser group for bidding in the keyword auction. In another embodiment, a method of generating a bid for a first advertiser for placement of a first advertisement in association with a search results list is provided. In another embodiment, an apparatus for generating the bid for the first advertiser is provided. Is still another embodiment, a method of coordinating bids from a first advertiser and a second advertiser for placement of at least one advertisement in association with a first search results list is provided.
U.S. Patent Application Pub. No. U.S. 2005/0071325 A1 discloses a system wherein the number of ads potentially relevant to search query information may be increased by relaxing the notion of search query keyword matching. This may be done, for example, by expanding a set of ad request keywords to include both query keywords (or derivatives of a root thereof) and related keywords. The related keywords may be words with a relatively high co-occurrence with a query keyword in a group of previous search queries (e.g., search queries in a session). The scores of ads with keyword targeting criteria that matched words related to words in a search query, but not the words from the search query, may be discounted. That is, the scores of ads served pursuant to a relaxed notion of matching may be discounted relative to the scores of ads served pursuant to a stricter notion of matching. This may be done by using a score modification parameter, such as an ad performance multiplier (for cases in which an ad score is a function of ad performance information). The score modification parameter may be updated to reflect observed performance data, such as performance data associated with {word-to-related word} mappings.
U.S. Patent Application Pub. No. U.S. 2005/0137939 A1 discloses a server-based method of automatically generating a plurality of bids for an advertiser for placement of at least one advertisement in association with a search results list. The method includes: a) receiving at least one candidate advertisement, b) creating a list of candidate keywords, c) estimating a click-through rate for each advertisement-keyword pair, d) calculating a return on advertising investment (ROAI) for each advertisement-keyword pair, and e) calculating a bid amount for each advertisement-keyword pair. In another aspect, a server-based method of generating a bid for placement of an advertisement in association with a search results list is provided. In other aspects, a method of selecting one or more keywords in conjunction with the bid is provided as well as a method of determining a return on advertising investment (ROAI) information for an advertiser in conjunction with the bid is provided.
U.S. Patent Application Pub. No. U.S. 2004/0088241 A1 discloses a “Keyword Automated Bidding System” (KABS) which, among other things, provides an intelligent system for bidders for a ranking in web search results list to determine bids and bidding strategies that maximize return on bid investments and help direct allocation of available funds for bids to keywords that lead to more optimal returns. An example embodiment is designed to generate a scalable solution to the problem of selecting the proper set of keywords to bid and the proper values of such bids for thousands of keywords on third party sites such as Overture and Google.com. The scalable solution is generated according to operator-defined model constraints and utility functions. In one embodiment, KABS maximizes profit by maximizing the Margin Rate to a bidder which is the difference in the aggregate Revenue per Redirect (RPR) from the merchants and the Cost per Click (CPC) that must be paid to the traffic source. The prime constraint on this solution is the total CPC dollar amount that is budgeted over a fixed interval of time (day, week, etc.). A major computational subsystem of KABS performs the estimation of arrival or click-thru rates for each keyword or category of keywords as a function of their display ranks on the source site. It is the form and level of this estimated function that is critical in the selection of the proper display rank from an active bid table a spider retrieves for each keyword. The KABS operator can be required to provide the inputs that direct and constrain the system's operation. Among these is the comprehensive set of keywords of interest from which the proper subset can be computed. Other key inputs include the frequencies of executing the various KABS from re-computing the arrival functions to regeneration of the bid set of keywords along with their corresponding bids and display ranks.
U.S. Patent Application Pub. No. U.S. 2004/0068460 A1 discloses a method and system enabling advertisers to achieve a desired ordinal position of a web page link in a list of search results generated by a bid-for-position search engine on the Internet in response to a keyword search. The method involves surveying other bid-for-position search engines to collect available bid data, determining a network high bid amount for a keyword of interest and the desired position, and adjusting the advertiser's bid on the keyword to be at least as much as the network high bid amount for that keyword and desired position.
U.S. Patent Application Pub. No. U.S. 2003/0088525 A1 discloses a method and apparatus (information processing system) for overcoming deficiencies and inefficiencies in the current paid search engine keyword bidding market, by providing keyword bidders with information they need to better optimize their use of paid search engines. The system accumulates bid amounts for a plurality of target keywords at one or more paid Internet search engines, and presents the bid amounts to a user, enabling the user to evaluate and optimize bids on those keywords. The system also presents bid amounts for a keyword at one or more paid Internet search engines, in a manner highlighting one or more selected bid amounts of interest to a potential bidder. This permits a bidder to identify the bidder's own bid, and/or to identify a differential in bid amounts that indicates an opportunity for bid optimization. The system further monitors keyword bids at one or more paid Internet search engines to identify bid changes of interest to a potential bidder.
U.S. Patent Application Pub. No. U.S. 2003/0055729 A1 discloses a method and system for allocating display space on a web page. In one embodiment, the display space system receives multiple bids each indicating a bid amount and an advertisement. When a request is received to provide a web page that includes the display space, the display space system selects a bid based in part on the bid amount. The display space system then adds the advertisement of the selected bid to the web page. The bid may also include various criteria that specify the web pages on which the advertisement may be placed, the users to whom the advertisement may be presented, and the time when the advertisement may be placed. The bid amount may be a based on an established currency or based on advertising points. The display space system may award advertising points for various activities that users perform. The activities for which advertising points may be awarded may include the listing of an item to be auctioned, the bidding on an item being auctioned, the purchasing of an item at an auction, or the purchasing of an item at a fixed price. The display space system tracks the advertising points that have been allocated to each user. When an advertisement is placed on a web page on behalf of the user, the display space system reduces the number of advertising points allocated to that user. The display space system may also provide an auto bidding mechanism that places bids for display space on behalf of the user.
U.S. Patent Application Pub. No. U.S. 2003/0055816 A1 discloses a pay-for-placement search system that makes search term recommendations to advertisers managing their accounts in one or more of two ways. A first technique involves looking for good search terms directly on an advertiser's web site. A second technique involves comparing an advertiser to other, similar advertisers and recommending the search terms the other advertisers have chosen. The first technique is called spidering and the second technique is called collaborative filtering. In the preferred embodiment, the output of the spidering step is used as input to the collaborative filtering step. The final output of search terms from both steps is then interleaved in a natural way.
U.S. Patent Application Pub. No. U.S. 2003/0105677 A1 discloses an automated web ranking system which enables advertisers to dynamically adjust pay-per-click bids to control advertising costs. The system tracks search terms which are used to market an advertiser's product or services in on-line marketing media (“OMM”). The system determines the search term's effectiveness by collecting and analyzing data relating to the number of impressions, the number of clicks, and the number of resulting sales generated by a search term at a given time period. Based on the data collected and parameters which the advertiser provides relating to the advertiser's economic factors, the system calculates a maximum acceptable bid for each search term. The system monitors the web for competitor's bids on an advertiser's search term and places bids which fall below the maximum acceptable bid.
United States Patent Application No. 2005/0223000 discloses a system and method for enabling information providers using a computer network to influence a position for a search listing within a search result list. A database stores accounts for the network information providers. Each account contains contact and billing information. In addition, each account contains at least one search listing having at least three components: a description, a search term comprising one or more keywords, and a bid amount. The network information provider may add, delete, or modify a search listing after logging into his or her account via an authentication process. The network information provider influences a position for a search listing in the provider's account by first selecting a relevant search term and entering that search term and the description into a search listing. A continuous online competitive bidding process occurs when the network information provider enters a new bid amount for a search listing. This bid amount is compared with all other bid amounts for the same search term. A rank value is generated for all search listings having that search term. The generated rank value determines where the network information provider's listing can appear on the search results list page that is generated in response to a query of the search term by a searcher at a client computer on the computer network. A higher bid by a network information provider can result in a higher rank value and a more advantageous placement.
United States Patent Application No. 2005/0065844 discloses a system and method for automating the management of an advertising campaign for a sponsored search application. An advertiser can easily manage their advertising campaign based on a budget and other information that they are most familiar with, e.g., the length of time for the campaign, desired number of total clicks during the campaign, the time zone of the campaign, keywords to be bid upon for the sponsored search application, the advertisement (copy and heading), and the URL associated with the location of the advertisement copy. With this relatively basic information provided, an example embodiment can automatically manage the bidding on both small and relatively large numbers of keywords for an advertising campaign.
United States Patent Application No. 2004/0230574 discloses a method and system for providing a set of search terms in response to a user input. A first set of search terms is selected from a master set of search terms based upon a match between the input and the search terms or based upon a predefined association between the input and the search terms. A second set of search terms is selected from the first set of search terms in response to a value score that is established for each of the search terms. The value score is selected based at least in part upon the amount of revenue that each search term generates for the system's operator.
United States Patent Application No. 2004/0199496 discloses a presentation system accepts presentations or references to presentations from prospective presenters. Some or all of the presentations or references are stored in a database and referenced by keywords such that presentations to be presented in response to particular searches can be identified. A presentation manager handles accepting bids and settling terms between prospective presenters. The results of such processes might be stored in a presentation details database. A presentation server handles retrieving presentations from the presentation details database for presentation to users along with requests such as search results. Both the presentation manager and the presentation server can operate on a keywords-basis, wherein presentation terms specify keywords to be associated with particular presentations and the presentation server serves particular presentations based on keywords in a search query for which the presentations are to be returned. The association of keywords can be done using canonicalization so that, under certain conditions, different keywords are treated as the same keyword. Canonicalizations might include plural/singular forms, gender forms, stem word forms, suffix forms, prefix forms, typographical error forms, word order, pattern ignoring, acronyms, stop word elimination, etc. Conditions might include aspects of the search query state, such as the user's demographics, the page from which the search query was initiated, etc.
U.S. Pat. No. 6,826,572 describes a system for advertisers to efficiently manage their search listings in placement database search system includes grouping means for managing multiple categories for the search listings and query means for searching search listings. The system further includes quick-fill means for modifying an attribute in a plurality of search listings by specifying the modification at a single location. The system provides a method and system for a pay for placement database search system. The method and system include grouping and querying, one or more search listings associated with an advertiser, and providing the advertisers an ability to simultaneously modify a plurality of search listings. The advertisers also possess means to search the categories and gather statistical data for an entire category.
U.S. Pat. No. 6,704,727 describes a method and system for providing a set of search terms in response to a user input. A first set of search terms is selected from a master set of search terms based upon a match between the input and the search terms or based upon a predefined association between the input and the search terms. A second set of search terms is selected from the first set of search terms in response to a value score that is established for each of the search terms. The value score is selected based at least in part upon the amount of revenue that each search term generates for the system's operator.
U.S. Pat. No. 6,876,997 discloses a method of generating a search result list and also provides related searches for use by a searcher. Search listings which generate a match with a search request submitted by the searcher are identified in a pay for placement database which includes a plurality of search listings. Related search listings contained in a related search database generated from the pay for placement database are identified as relevant to the search request. A search result list is returned to the searcher including the identified search listings and one or more of the identified search listings.
Thus, a computer-implemented method and system for keyword bidding are needed.
Embodiments illustrated by way of example and not limitation in the figures of the accompanying drawings, in which:
a and 2b are a block diagram of a computer system on which an embodiment may operate.
A computer-implemented method and system for keyword bidding are disclosed. In the following description, numerous specific details are set forth. However, it is understood that embodiments may be practiced without these specific details. In other instances, well-known processes, structures and techniques have not been shown in detail in order not to obscure the clarity of this description.
An example embodiment of a computer-implemented method and system may manage keyword bidding prices. Initially, a host may develop and maintain a portfolio of keywords for which users can bid. In a manner described in detail in the above-referenced related patent applications, a host can search and select desired keywords for the portfolio and cluster the keywords into logical groups based on a variety of dimensional metrics. A data mining process is used to implement keyword affinity scoring. Clustering combines keywords into logical groups or clusters that share a similar behavior with respect to a considered dimension (or creative). A creative can be a template advertisement or message into which a keyword can be inserted. Sources for clustering techniques include: (1) “ex ante” information about a keyword (linguistic similarity, number of words in the keyword phrase, supply-side categorization etc.); (2) performance metrics (costs, clicks, return on investment (ROI), NS saturation, competitors, use of item level metrics, etc.); (3) internal sources (e.g., host search query history, host catalogues, host listings parsings, host affiliate query, catalog, and listing information, international search strings, paid search queries, etc.); and (4) external sources (e.g. Googspy, Yahoo buzz, etc.).
The computer-implemented method and system may also determine and use a correlation between different search queries in a single session. The correlation uses information based on the proximity of the different search queries and the subject matter searched in each query. For example, if a user submits a first search query (e.g. “John”) and then subsequently in the same session submits a second search query (e.g. “John Smith”), a correlation can be drawn between those two keywords. This correlation can be used to form reasonable inferences related to the user behavior; because two related search queries appeared in sequence.
The performance metrics for a particular keyword or keyword cluster include a calculation of the value of a new user based on keywords. The effective use of advertising or messaging as related to keyword search queries enables the host to attract new users as a result of keyword based advertising. The effectiveness of a particular keyword or keyword cluster to attract new users is a key performance metric. One measure of this effectiveness is a Revenue per Click (RPC) scoring. If a particular keyword or keyword cluster and a related advertisement or message causes a user to click a link or icon, a certain value for that click through action can be calculated using and RPC scoring. RPC scoring is based on a predicted value for a given keyword. The keyword scoring concept includes calculating the value of a new user brought in by a specific keyword or keyword cluster. In an example embodiment, as described below, additional data can be used to actually project a value forward in time. For example, a particular click-through might be worth $10 a click yesterday. However, there may be strong evidence the click-through is going to be worth $12 a click tomorrow, because of certain consumer variables that were observed (e.g., the volume of related listings may have skyrocketed, conversion rates may be skyrocketing, and ASPs are staying flat). Conversion is the act of a user clicking, responding, or otherwise taking action related to an advertisement or message. These consumer variables suggest that the keyword is going to be worth more tomorrow and into the future. In the example computer-implemented method and system, this forward looking analysis is done with the use of data mining and statistical analysis.
Revenue Per Click (RPC) prediction is one building block for keyword scoring and value prediction. For this reason, it is desirable that the model be as accurate as possible. At its core, the example RPC prediction process described herein is a statistical approach to ascribing the likely future revenue for a given click for a given keyword. There can be a large number of potential inputs to this RPC prediction, including: past revenue and past click volumes, COFA (Category of First Activity) for users who have converted on a given word, or the Bid Density by Category for a keyword historically. In the end, a large number of x-variables can be used as inputs to the model while only a few inputs may actually be part of the calculation. However, because the relative weighting of the various variables (and even the variables themselves) is likely to change over time, the example computer-implemented method and system provide an extensible and flexible approach towards the RPC calculations.
To best use the example RPC model, the input data to the RPC model may be updated on a periodic basis, thus incorporating the newest information. This periodic update can be implemented by interfacing the RPC model with the Keyword Selection Module and the Keyword Datamart (KWDM) described in related patent applications referenced above. The efficiency of the RPC model can also be improved if the RPC model receives warning alerts as soon as possible if there is a problem with the periodic retrieval of RPC model input data.
One theme of the RPC modeling is global scalability, which includes international country-specific models using the same methodology as has been implemented for the RPC model in the US. This implies that the RPC model may be based on readily available data sources in every country. Country-specific RPC models are implemented for individual countries and for individual search engines to improve the regional accuracy of the RPC modeling.
As part of the periodic (e.g. daily) input data gathering process, the RPC Predictive Model may pull in keyword/user/category data from various internal and external sources that have been identified as potential predictors of a host's keywords' RPC and number of clicks. Various sources for this keyword data originate as described in the above referenced related patent application. Specifically, the keyword data can originate through the Keyword Testing Complex.
The Keyword Testing Complex is a shorthand name for the sourcing, selecting, adding, reporting, and deleting keywords cycle. The principal aim of this functionality, as described in detail below, is to facilitate the adding of good keywords and deleting of bad ones, provide control and reporting so users can easily run tests to determine the heuristics that matter in keyword selection and retention, and enable the automation of as much of the keyword testing, selection, and retention cycle as possible.
Referring to
The Keyword Sourcing Module 322 regularly pulls in keyword data from various internal and external sources that have been identified as potential sources of potentially revenue-generating keywords. Because each data source may have different dimensions and attributes, a generic and extensible data model is required. It is unlikely that many configurations settings or controls may be required to support keyword sourcing. A user of the technology described herein, denoted as a host, can use the Keyword Sourcing Module 322 to collect an initial unfiltered set of keywords from various sources. The following are some examples of important keyword sources that can be used. It can be apparent to those of ordinary skill in the art that other sources of keywords can similarly be used. Also note that there may likely be additional keyword sources that are important to various companies, organizations, countries or regions.
Internal—Host Individually
Internal—Host Combined with 3rd Parties
External: (Well Known Sources of Keywords, e.g.)
Ad Hoc
As related to RPC modeling, keyword data can be sourced using the Keyword Testing Complex and the Sourcing Module 322. In addition, other keyword data sources include the following.
Cost
Revenue
Retention Bidders
Retention Bids
Acquisition Bidders
Acquisition Bids
ACRU's
Clicks
Average Position
Category Percentage Weighting
Site ID
Meta Category
Level 2
Level 3
Level 4
Level 5
Level 6
Category Percentage Weighting
Site ID
Meta Category
Level 2
Level 3
Level 4
Level 5
Level 6
ASP
Conversion Rate
Success Item Count
Revenue
External Category Clustering
Sets—Retained Bidders, Acquired Users
User
Value
RFM
Zip
CoFA—(Category of First Activity)
Mosaic
Demographic
Keywords in the KWDM 320 may contain various levels of dimension data. For example: 1) global dimensions (e.g. linguistic dimensions), 2) traffic dimensions (internal and external data), 3) clustering dimensions, and 4) source specific metrics. These dimensions are described in more detail below. Because many of these dimensions change from day to day, the aggregator 326 defines a time period of measurement for each metric. It may not be necessary to repopulate all of these metrics every day for every keyword. A weekly, monthly or quarterly refresh may be sufficient in some cases. A mechanism to track the source (and number of occurrences per source) by keyword is also a desired feature. As examples of dimensions (non-exhaustive):
a. Global Dimensions
b. Traffic Dimensions
c. Clustering Dimensions
d. Source-Specific Dimensions (extensible)
Referring to
The Keyword Selection Module 330 is shown in
Manual Method
Automatic Method
The computer-implemented method and system for keyword bidding disclosed herein provide a set of data-driven controls that allow users to manage keyword bidding prices at the keyword level and at a large scale. The computer-implemented method and system include a rules engine to manage the spend associated with purchasing and managing a keyword portfolio. The data-driven controls include controls to manage spend and high-volume. A few of the features of an example embodiment include the following:
CPC Bid Optimization of example embodiments described herein is an element to trafficking keywords and ensuring a host is maximizing its return on investment (ROI) on each keyword purchase. Because different search engines have different interfaces, policies, and rules associated with keywords and paid search opportunities, an automated bid optimization system may have to take these search engine-specific differences into account. Below are example considerations for search engine-specific bidding methodologies (e.g. Google and Yahoo!). Based on each search engine's current bidding methodology, specific business rules and a customized RPC Predictive Model has been created as part of the computer-implemented method and system described herein that can enable more efficient CPC bid optimization.
Sample Components:
Input A:
Input B:
Input C:
Based on a current scaled TPC (target per click) value, use the Competitor Bid Landscape to determine a Bid value, Deviation=abs[TPC−CPC(pos±1,2)] ($), and the position ±1, ±2 relative to our current position. The TPC is a desired bid value the advertiser is caning to pay. Clearly, the advertiser seeks to optimize the TPC so the lowest value is paid while retaining an acceptable level of user click-throughs. The current position corresponds to a location on a search results page relative to the position of other advertiser's (competitors) on the same page in relation to the same keyword. Typically, a search engine can position a highest bidder's advertisement at the top (or in the position most likely to attract user click-throughs) of the search results page. The next highest bidder's advertisement is positioned just below the highest bidder's advertisement. This ranking continues until there is no space left on the search results page or the number of advertisements exceeds a search engine's maximum. In this manner, the search engine's advertisement placement corresponds to keyword bid values and the corresponding number of expected user click-throughs. As is well known, a search engine is paid the bid value by the advertiser for each user click-through.
For example, take the keyword example “maple wood”. The bid landscape tells us that we are currently paying $0.27 for position 3. “Position −1” places us in position 2 (a better position than position 3 in terms of the number of expected user click-throughs) with a maximum bid of $0.27 and the deviation of ˜$0.03 from our scaled TPC of ˜$0.25. “Position −2” places us in position 1 (a better position than position 2 in terms of the number of expected user click-throughs) with a maximum bid of $0.28 and the deviation of ˜$0.04 from our scaled TPC.
Using the bidding logic shown above, these metrics are determined for the two positions above and below the current position. From there, the minimum deviation is selected from the four surrounding positions. Once the optimal gap is determined, a new maximum CPC is determined based on the following:
If the Minimum Deviation lands the keyword between position 1 and 2, [new CPCmax=scaled TPC]
If the Minimum Deviation lands the keyword between positions >2, [new CPCmax=CPChi−$0.01] or the default minimum of $0.10.
In all cases, the [CPCactual=CPClow+$0.01] and [CPCceiling=TPC*(1+X)], where X=scalable margin.
Output:
Using the process described above, parameters are generated for a sample Yahoo bidding strategy. These parameters can be used to create the XML syntax to make the appropriate CPC changes through the API.
Sample Components:
Input A:
Input B:
Input C:
Based on a current scaled TPC (target per click) value, use the previous day's CPCmax and previous day's keyword-level data to calculate:
[$ Deviation]=[TPC−CPCavg] A.
[% Deviation]=[$ Deviation]/TPC B.
Calculated CPCmax=(1+% Deviation)×[previous day's CPCmax] C.
CPCceiling=TPC*(1+X)], where X=scalable margin D.
The new CPCmax may be calculated based on the following logic:
New CPCmax may be bounded by the following rules:
For example, take the keyword example “longaberger pottery” and the corresponding sample parameters below.
Based on the bidding logic above, since (A≠n/a) and [(previous day's CPCavg)≦1.5] is true, then:
CPCmax=min(D,previous day's CPCmax)=min(0.85,0.77)=0.77
Output:
Using the process described above, parameters are generated for a sample Google bidding strategy. These parameters, including the new CPCmax, can be used to execute the corresponding bid changes through Google's API.
Variations of the bidding processes described above can be used to support other search engines. Further, a generic version of the bidding optimizer described herein can output or export a flat file for manual loading on other platforms. In addition, variations of the bidding processes described above can include time of day/hour optimization and demographic targeting.
The Match Type Automation functionality provided in the computer-implemented method and system described herein enables a host to automate the decision-making process as to which keywords to buy on the different Match Types offered by the conventional search engines (e.g. Advanced/Standard match types on Overture, and Broad/Phrase/Exact match types on Google).
In particular, the functionality of the present computer-implemented method and system automates the decision-making related to:
In addition, the functionality of the present computer-implemented method and system also provides additional functionality. When submitting keywords to buy on a search engine, the user can specify the desired Match Type. The user can check the Match Type status of any keyword, list of keywords, or keyword cluster at any time. The user can also manually change the Match Type status of any keyword, list of keywords, or keyword cluster at any time. When an embodiment is about to switch some existing keywords from an Advanced match type to a Standard match type, the embodiment generates a report specifying the list of keywords that have been recommended to be switched over to Standard Match. The embodiment advises the user of the recommended changes prior to trafficking the changes. An example embodiment also allows the user to switch from Advanced to Standard match type automatically on a periodic basis (e.g. monthly). Alternatively, the match type switching can be configured to occur only after being accepted by the user, in the event the user wishes to review the recommended list of words first. This would enable the ability to override recommendations.
Some conventional keyword processing systems store even the slightest differences in user queries as distinct queries/records. For example, two phrases may have the same keywords, but one may have an additional space in the keyword string. Conventional systems create distinct records for these keyword variations even though these variations would be considered the same keyword in some conventional search engines (e.g. Overture's Match Driver Logic), thus triggering the display of the same advertisements. Thus, it is beneficial to be able to mimic the Match Driver Logic of a particular search engine to the extent possible. The following pre-processing actions can be implemented to increase the likelihood that the keyword processing can mimic the operation of the Match Driver Logic of a particular search engine.
The following actions can be used in various embodiments to process user queries and related keywords for various conventional search engines.
A particular example embodiment includes an advertising platform, allowing sellers on a host site to buy and create advertisements for their items for sale and their stores selling items.
Advertiser Portal (1316)—End user facing application. The Advertiser Portal can allow registered users to manage their Paid Search portfolio across various publishers. The portal user interface (UI) can support various functionality, including:
As shown in
Administrative Application (1320)—Customer Support and Program Administration
Billing (1318)—Send invoices, collect payments, and journal to SAP
Ad Serving and Tracking (1310)—Show ads on publisher sites
Ad Search (1312)—Find the right ads to show
Event Tracking Logic (ETL) Infrastructure (1314)—Track and aggregate all the data that drives the platform
Third Party Applications (1322)—Automated creation of distributed commerce campaigns for 3rd party merchants.
In addition, to support system and administrative functionality, administrative (admin) users and the system can have the ability to set statuses for the following:
The Advertiser Portal 1316 can ultimately support a wide-variety of ad formats, including rich media, and can be designed to support this type of scaling.
The Account Overview is the page that can be displayed to the user when they first log-in. The page can contain a snapshot of their account, including the following:
Users can be allowed to toggle start and end date fields to control the range of the Account Performance metrics.
From this page, users can see a list of the Campaigns that have already been set up along with various metadata and metrics. The following data can be displayed:
There can also be an ‘Edit Campaign’ link for each saved Campaign. Clicking on a Campaign Name can forward the user to its Campaign Dashboard. The users can have the option to delete campaign(s) from the Account Dashboard. Deleting a campaign can remove the campaigns and all ad groups within that campaign from the dashboard view and the system permanently. User can be prompted for delete confirmation “Are you sure you want to delete?” before the deletion takes place. Aggregated reporting data can be available as a summary of all deleted objects on all Dashboards. Pausing a campaign suspends activity on all Ad Groups contained within that campaign. Users can still modify campaign attributes while it is in a paused state. The Campaign list can be filtered by ‘All’ (default) or ‘Active Only’. Users can also specify a date range for the metric calculation. The list can be sortable by all fields. The page can have multi-select checkbox functionality to allow users to make status changes to multiple campaigns at once—including activation, pausing and deletion. Users must confirm all status changes (pop-up alert) before they are applied.
From this page, users can see detailed data for a saved campaign, including:
The Campaign Dashboard can also display a list of Ad Groups saved for that account along with detailed data for each, including:
An ‘Edit’ link can also be displayed for each Ad Group that can forward the user to the ‘Edit Ad Group’ flow. Clicking on the Ad Group Name forwards the user to the Ad Group Dashboard. Users can have the option to delete ad group or category from the Campaign Dashboard. Deleting an ad group can remove the ad group and all keywords within that ad group from the dashboard view and the system permanently. User can be prompted for delete confirmation “Are you sure you want to delete?” before the deletion takes place. Reporting data can be available as a summary of all deleted ad groups on Campaign Dashboards.
On the ‘Create Campaign’ page, users can have the ability to create one new campaign at a time. Users can be prompted for the following information:
The daily budget (along with all other monetary parameters) can utilize the currency set at the account-level. The optimization engine infrastructure can be designed to allow multiple targeted countries per campaign. Clicking on the “Continue” button can forward the user to following:
From the Campaign dashboard, users can have the ability to click an ‘Edit’ link for each saved campaign. From this page, users can be allowed to edit the settings for individual Campaigns, including:
Users cannot be allowed to edit the campaign-type setting (from keyword to category, or visa-versa). Users can have the ability to change the Country that is targeted.
From this page, users can see detailed data for a saved Ad Group, including:
From this page, users can also manage the status for creatives (active or inactive) and delete creatives. Users can also view keyword-level data for keyword-targeted Ad Groups, including:
Users can also click a Bulk Edit link. After clicking the link, the following data in the keyword reporting table can be displayed as an editable text input box:
The data above cannot be displayed for Category-targeted Ad Groups. Instead, the following data can be displayed:
From the Create Ad Group flow, users can have the ability to create new Ad Groups for a campaign. The creation process can differ for keyword-targeted and category-targeted campaigns.
Users can have the ability to create one new Ad Group at a time for keyword-targeted Campaigns. During the Ad Group creation process, users can have to enter basic Ad Group information, enter keywords to associate with the Ad Group and finally create the advertisements (creatives) to associate with the Ad Group. During the first step of the Ad Group creation flow, users can be prompted for the following basic information:
Users can also enter a list of keywords into a free-form text box—one keyword per line—and enter a default Max CPC value for the set of keywords. Keyword tagging (board and exact) can be supported in the Ad Portal to indicate matchtype (exact match keywords can be contained within double quotes). All keywords can be normalized as follows (with no notification to the user):
Only the following characters are allowed in keyword strings in a particular embodiment:
Allowed special characters: . ′ / - <space>
Allowed German characters:
Allowed alphanumeric characters: a through z, 0 through 9.
Inclusion of any special characters not on the lists above can trigger an error message. If a user enters a duplicate with the same matchtype in the list of keywords when creating or editing an ad group, the duplicate can be dropped and no error message can be displayed.
After clicking the ‘Continue’ button, users can be forwarded to the next step where they can have the ability to create advertisements (Creatives), which includes Ad text, an Ad image (optionally) and a destination URL (Landing Page) for the Creative. Upon choosing a Creative-type, users can be presented with a form to enter their Creative details. For each creative, users can enter the following fields:
In addition, we should verify that the specified Destination URL is a valid link, and the domain of the Display URL matches the domain of the Destination URL. They can also have the option to upload an Ad Image for the creative. Uploaded images can be automatically resized and formatted in-line with publisher ad image requirements before being stored in the server. The link to the image on the server can be stored in the Ad Portal database. Users can have the ability to optionally insert a (keyword) replacement tag within their creative text that can be substituted with the keyword string (not the search string) before being served. However, a (keyword) replacement tag may not be supported for category campaigns.
Users can specify their keyword insertion criteria by inserted the following into their creative text (headline, line 1, line 2 and/or display URL) and Landing Page field at the Creative level: {param1:param2}
Creative field length restrictions should be applied by the Ad Portal by comparing the summed character count of the backup string plus the non-tag portion of the creative text against the limit. For example, the creative line, “Looking for {keyword:cool stuff}” should be considered to have 22 characters. If the length restriction is exceeded, a message should be displayed to the user. In a particular embodiment, only the following special characters are allowed in creative strings:
Allowed special characters: # $ & _ - “ [ ] ′ + . , / : % ? ! ® ™ <space>
Allowed German characters:
Allowed alphanumeric characters: A through Z, a through z, 0 through 9
Inclusion of any characters not on the lists above should trigger an error message. For both creative- and keyword-level landing pages, the domain of the display (friendly) URL must match the domain of the destination URL. This rule can be enforced by the Ad Portal. In addition, if the Destination URL is for a host item listings page, a call to a host API can be made to ensure that the item has been approved. After the user has entered data for a creative, they can have the option to either ‘Continue’ (if they do not need to add any more Creatives) or ‘Save and Create New’. If they click the latter, the saved preview for the Creative can be displayed at the bottom of the page (along with any other saved creatives), and the user can have the ability to repeat the process to add another Creative. In a particular embodiment, we can allow five creatives per Ad Group (with the ability to increase this limit to 10). After the user has entered their last Creative, they can click the ‘Continue’ button to proceed to the keyword-level data setup page.
After clicking the ‘Continue’ button, users can be forwarded to the next step where they can have the ability to optionally alter the CPC value and landing page for each of the keyword-matchtypes they entered earlier. Keyword-level landing pages are optional—if a user has not chosen a keyword-level landing page for a particular keyword, the creative-level landing page can be used instead. Keyword-level Max CPC values are optional—if a user has not chosen a keyword-level Max CPC for a particular creative, the Ad Group-level Default Max CPC can be used instead. At this point the user has completing entering all of the necessary information for their new Ad Group. During this last step, users can have the ability to review the details of their Ad Group to make any necessary changes before they click the ‘Create’ button to complete the process. By clicking “Create”, user can be prompt with “create another ad group?” option. If user chooses “yes”, user can be directed to create a new ad group within the same campaign; selecting “no” can direct users to campaign dashboard.
The Ad Group creation process for category-targeted campaigns can be designed to facilitate multi-category targeting. From a single flow, users can have the ability to associate multiple categories with a single set of Creatives. Users can have to go through the creation flow for each distinct Creative Set that they wish to create. The application can create one new Ad Group per category.
During the first step of the Ad Groups creation process, users can be prompted to select the categories for targeting. Users can have the ability to navigate through the Ad Portal category tree structure and add categories to the targeted list. Tree level can be shown wherever category name is displayed. In addition, users can have the ability to specify a default CPC that can be applied to all Category Ad Groups (they can modify this on a per-category basis later). After clicking the ‘Continue’ button, users can be forwarded to the next page in the flow—CPC selection. On this page, users can select a Max CPC value for each of the categories selected in the first step. The next step in the process can be the Creative Set and Landing Page selection. The UI for this page can be the same as the corresponding page in the keyword-targeted Ad Group flow.
At this point the user has completing entering all of the necessary information for their new category-targeted Ad Groups. During this last step, users can have the ability to review the details of their Ad Groups to make any necessary changes before they click the ‘Create’ button to complete the process. The application can create one Ad Group per selected category. Users cannot have the ability to assign keywords to category-targeted Ad Groups. Instead, the application can maintain a keyword list for each category. This list can be hidden from the user completely. The application can manage optimization and external partner bidding at the keyword-level (with the Ad Group-level Max CPC bid used for all keywords), but all category-targeted reporting (both UI and downloadable reports) can be summarized at the Ad Group (category) level.
The Ad Portal can leverage the host product/service category structure, with the following assumptions:
We can assume the following:
It is assumed that the real-time optimizer can only optimize for a keyword (search query string), not category, therefore:
The Ad Portal can distinguish between the two category-keyword mappings above so that they may be interpreted differently by the Offline Optimization job.
For both keyword-targeted and category-targeted campaigns, users can only have the ability to edit one Ad Group at a time. When selecting the ‘Edit Ad Group Settings’ link from the Ad Group dashboard, users can be forwarded to a page where they can modify the following Ad Group settings:
Users cannot have the ability to edit the category setting in category-targeted Ad Groups. Edit Creative can be treated as delete existing creative and adding a new one. Performance data for the edited creative can be lost. Edit Landing Page is considered an update (but not delete/add) and performance data can be maintained.
From the Ad Group dashboard, users can have the ability to click on individual keywords to modify their properties. From the Edit Keyword page, users can modify the following:
There can be minimum bid and maximum bid set at the portfolio level for both keyword and category Max CPC (cost per click) and can be stored in US dollars in the database. In addition, there can be minimum bid sets for individual keyword Max CPC and can be stored in US dollars in the database. During Ad Group creation, there may not be a validation on the UI (user interface) for the keyword Max CPC entered by user against portfolio-level minimum/maximum bid and keyword-level minimum bid. Once the Ad Group is saved, Max CPC for each keyword (if no Max CPC is defined for the keyword, use Ad Group's default Max CPC) can be checked against portfolio-level minimum/maximum bid and keyword-level minimum bid. If the Max CPC is higher than the maximum bid (portfolio), an error message can be shown: The Max CPC for the following [keyword/ad group] has exceeded the maximum allowable amount of [amount in local currency]: [keyword/ad group]
If the Max CPC is lower than either of the minimum bid (portfolio, keyword-level), the status of corresponding keyword can be changed to “inactive” with reason code “below minimum bid”. There should be UI message “Please increase your Max CPC for this keyword” next to the corresponding keyword in Ad Group dashboard. When the Max CPC of the ad group is updated, the same validation should be triggered for all keywords without a defined Max CPC. If the updated Max CPC is higher than the maximum bid, an error message can be shown: The Max CPC for the following [keyword/ad group] has exceeded the maximum allowable amount of [amount in local currency]: [keyword/ad group]
If the updated Max CPC is higher/equal to the minimum bid (but below the maximum bid), the status of the corresponding keyword(s) can be changed from “inactive” to “inactive (user paused)”. **Only keyword with the “inactive” status with reason code “below minimum bid” is eligible to be changed to “inactive (user paused)”. In addition, the same validation should be applied to each keyword when Max CPC of that keyword is updated. If the updated Max CPC is higher than the maximum bid, an error message can be shown: The Max CPC for the following [keyword(s)] has exceeded the maximum allowable amount of [amount in local currency]: [keyword1, keyword 2, keyword 3]
If the updated Max CPC is changed to NULL or higher/equal to the minimum bid (but below the maximum bid), the status of the corresponding keyword can be changed from “inactive” to “inactive (user paused)”. Only keyword with the “inactive” status with reason code “below minimum bid” is eligible to be changed to “inactive (user paused)”.
If a user's Max CPC at the category level exceeds the max bid, show an error message to the user that says the following: The Max CPC for the following [category] has exceeded the maximum allowable amount: [category name]
If a user's Max CPC at the category level is below the min bid restriction, do not show an error to the user and just set the status of that category to inactive with a reason of “below minimum bid”. The user's Max CPC at the category level should be checked against both the portfolio min/max requirement AND the category-level min requirement (if set). It must satisfy the restrictions at both levels. This check should be made both during creation and if the Max CPC is edited. If a category has a status of Inactive (Below Min Bid) and the Max CPC is edited and is no longer below the minimum bid restriction, the status should be changed to Inactive (User Paused) so that the user can decide when to activate it. The minimum bid and maximum bid can be applied for all keyword matchtypes. Keyword Ad Group's status will not be affected in respect to the minimum bid and maximum bid value. During each validation, the minimum and maximum bids stored in US dollars can be converted real time using the latest conversion rate in the database to the currency of the user's account.
From the Account Information page, users can have the ability to view and modify personal information and billing information.
Changes made to user Ad Portal account settings cannot propagate to the user Publisher Portal settings. The following fields can be displayed and can be modified (with the exception of the Country field):
Billing information can be set separately for users' Publisher and Advertiser Portal accounts.
Reporting data can be available in the following UI pages:
Users can have the ability to export reporting data from each dashboard view. Exported report can be the complete data set (not just the current page) without pagination. Existing Publisher file format for UI reporting can be used, i.e. excel or tab delimited text files. For both the UI view and export, users can have the ability to specify a date range for the report where range restriction can be the same as the UI view. Historical data can be available for the previous 6 months. All monetary data elements can be displayed with the currency set for the Account.
In
In
In
In
In
In
ALL click events, even those marked as fraudulent, can be sent to Mediaplex. Impression events may not be sent to Mediaplex. Any impression or click event that is flagged as filtered must not do any of the following:
Because click processing may apply real-time and off-line click and impression filtering, it may be necessary to reconcile against the list of correlated events that are returned in the Mediaplex data feed.
An Ad Unit is created for each distinct combination of the fields above. The real-time optimizer can optimize at the Ad Unit-level. Note that the system can allow scalability of the Ad Unit dimensions. It is understood that the system can optimize on additional dimensions. An Ad Unit can automatically be assigned to an Ad Unit Group by a scheduled batch job based on defined rules. The Optimization Management Console can allow administrative users to control scoring at the Group-level by manipulating Group settings and Scoring Model assignment.
From the Console UI, users can have the ability to set the following parameters for each Ad Unit Group:
A Scoring Model is a set of defined parameters (coefficients) that are applied to a set of variables. Users can create Scoring Models outside of the Ad Unit Group creation and assignment flows. Users can set the following basic criteria for a Scoring Model:
Users can then assign coefficients to the various scoring parameters. Parameters can be one of the following types:
From the Console UI, users can have the ability to assign Scoring Models to an Ad Unit Group. Users can assign multiple models to a single Ad Unit Group (up to a max limit), and a single model can be applied to multiple Ad Unit Groups. An Ad Unit Group is not considered active (and cannot be processed by the Offline Optimizer), unless it has at least one model assigned to it. After users have selected the models to associate to the Ad Group, they can enter their rotation distribution settings. Users can set a rotation percentage for each model. The rotation percentages can be defaulted to 1.00/[# of models] and must add up to a total of 1.00 (100%).
From the Console UI, users can have the ability to assign Scoring Models to an Ad Unit Group. Users can assign multiple models to a single Ad Unit Group (up to a max limit), and a single model can be applied to multiple Ad Unit Groups. An Ad Unit Group is not considered active (and cannot be processed by the Offline Optimizer), unless it has at least one model assigned to it. After users have selected the models to associate to the Ad Group, they can enter their rotation distribution settings. Users can set a rotation percentage for each model. The rotation percentages can be defaulted to 1.00/[# of models] and must add up to a total of 1.00 (100%).
In a particular embodiment, the Optimizer can include an offline optimizer and a real-time optimizer. The offline optimizer can generate rule sets for use by real-time optimizer. The Offline Optimizer is a batch job that calculates the Offline score for every active Ad Unit. An Ad Unit is a container that represents the most granular level of ad detail for which we can optimize. This can include:
An offline score may not be factored into the real-time optimization model, but the infrastructure can be designed to support real-time optimization based on both CPC (cost per click) and an offline score. For category-targeted Ad Groups, users may not have the ability set or manage keyword-level data in the Ad Portal UI and keyword-level data may not be present in the Ad Portal campaign tables. Instead, a mapping can be maintained between each Ad Portal category and a keyword list. The optimizer can use this mapping to generate keyword-level Ad Units for category-targeted Ad Groups, while assuming the following:
At the conclusion of the Offline Optimizer run, the Ad Unit identifying information (including Max CPC) and additional data necessary for ad serving can be pushed into memory for access by the Real-time Optimizer. The Offline Optimizer can send over a static Model ID along with the data above for access by the Real-time Optimizer. Doing this can minimize the infrastructure and code changes that would be necessary once the system is enhanced to support multiple models.
During real-time operation, the RTM can make an ad request call to the Ad Server (see above). The following data passed in from RTM can be relevant for ad optimization by the Ad Server:
The Ad Server can do the following before making a call to the Real-time Optimizer:
The Ad Server can make a call to the Real-time Optimizer, passing in the following data:
Based on the parameters above, the Real-time optimizer can determine which ads should be served. To do this, the optimizer can calculate a final score per qualifying Ad Unit per model, and serve the top n ranked ads (where n is the number of ads requested by RTM). In order for an Ad Unit to qualify, it must satisfy the following criteria:
If users have inserted a {keyword} replacement tag within their creative text, it can be substituted with the keyword string (not the search string) before being served. For qualifying Ad Units, a final score can be determined per Ad Unit per model by using the following parameters:
The Match Score is a static multiplier that can applied based on the degree to which a keyword matches the search string passed in by RTM. For exact match keywords, a constant multiplier can be applied to all keywords (this may be 1.0). For phrase match keywords, the degree of the keyword match can be determined by the following formula:
Degree of Match=(# of words/tokens in keyword string)/(# of words/tokens in search string)
For each “degree of match” range, we can maintain a match score multiplier that can be applied for phrase match keywords that fall in that range. It can be assumed that the ranges can cover 0-100% without any gaps or overlaps. The factors that determine the Match Score may not be configurable through any user interface, but it should be designed in a way that allows modifications on an infrequent basis.
For a segment of served ads, a degree of randomness (Perturbation Factor) can be applied to the final score for eligible Ad Units before the final ranking is determined. The Perturbation Factor is a dynamic multiplier that can conditionally apply a degree of randomness for a segment of served ads. We can making the following assumptions:
The Real-time Optimizer applies all of the multipliers above to the Max CPC for each Ad Unit to determine the Effective CPC (eCPC) for each. The Optimizer can return the top n ranked ads by eCPC (where n is the number of ads requested by RTM) to the Ad Server, which can then pass the data back to RTM (see above). The Optimizer may not return more than one ad from the same Account (Advertiser) for a single RTM call. In addition, no more than one ad per account (advertiser) should be served per RTM call.
For example, in reference to the table below, if RTM requests 5 ads for the search string “nintendo wii remote”, Optimizer may determine that ads 1-5 below should be served:
In order to determine the Actual CPC (the amount actually charged for a click) for each served ad, we can use the Vickrey Auction model. The Actual CPC for each served ad can be the minimum between:
An additional multiplier may be applied globally on top of the value above to determine the final Actual CPC value. In this case, the assumption is that the multiplier can be less than 1.00 to ensure that the final Actual CPC value is not greater than the Max CPC value. In the example table above, if the Actual CPC multiplier is 1.00, the top ranked Ad Unit would have an Actual CPC value of $0.57. Ad Unit #5 would have an Actual CPC of $0.12.
A particular embodiment includes other features enabled by the design structures described above. These features can include: 1) Keyword Bidding by Category, and 2) Category Moniker.
In a particular embodiment of the Keyword Bidding by Category functionality, the association of keywords and category can build an affinity between keywords and categories. This affinity can be used to create an ad format with bidding on keyword & category level. ‘Category’ functionality can extend to other grouping functions, linked with host content including a host category hierarchy. In a particular embodiment of the Keyword Bidding by Category functionality, an example method can include the following operations:
In a particular embodiment of the Category Moniker functionality, an example method can include the following operations:
Referring now to
Using one of a variety of network connection means, server computer 100 can communicate with client computers 150 using conventional means. In a particular implementation of this network configuration, a server computer 100 may operate as a web server if the Internet's World-Wide Web (WWW) is used for wide area network 110. Using the HTTP protocol and the HTML coding language across wide-area network 110, web server 100 may communicate across the World-Wide Web with clients 150. In this configuration, clients 150 use a client application program known as a web browser such as the Internet Explorer™ published by Microsoft Corporation of Redmond, Wash., the user interface of America On-Line™, or the web browser or HTML renderer of any other supplier. Using such conventional browsers and the World-Wide Web, clients 150 may access image, graphical, and textual data provided by web server 100 or they may run Web application software. Conventional means exist by which clients 150 may supply information to web server 100 through the World Wide Web 110 and the web server 100 may return processed data to clients 150.
Having briefly described one embodiment of the network environment in which an example embodiment may operate,
An optional data storage device 228 such as a magnetic disk or optical disk and its corresponding drive may also be coupled to computer system 200 for storing information and instructions. Computer system 200 can also be coupled via bus 216 to a display device 204, such as a cathode ray tube (CRT) or a liquid crystal display (LCD), for displaying information to a computer user. For example, image, textual, video, or graphical depictions of information may be presented to the user on display device 204. Typically, an alphanumeric input device 208, including alphanumeric and other keys is coupled to bus 216 for communicating information and/or command selections to processor 220. Another type of user input device is cursor control device 206, such as a conventional mouse, trackball, or other type of cursor direction keys for communicating direction information and command selection to processor 220 and for controlling cursor movement on display 204.
Alternatively, the client 150 can be implemented as a network computer or thin client device. Client 150 may also be a laptop or palm-top computing device, such as the Palm Pilot™. Client 150 could also be implemented in a robust cellular telephone, where such devices are currently being used with Internet micro-browsers. Such a network computer or thin client device does not necessarily include all of the devices and features of the above-described exemplary computer system; however, the functionality of an example embodiment or a subset thereof may nevertheless be implemented with such devices.
A communication device 226 is also coupled to bus 216 for accessing remote computers or servers, such as web server 100, or other servers via the Internet, for example. The communication device 226 may include a modem, a network interface card, or other well-known interface devices, such as those used for interfacing with Ethernet, Token-ring, or other types of networks. In any event, in this manner, the computer system 200 may be coupled to a number of servers 100 via a conventional network infrastructure such as the infrastructure illustrated in
The system of an example embodiment includes software, information processing hardware, and various processing steps, which can be described below. The features and process steps of example embodiments may be embodied in machine or computer executable instructions. The instructions can be used to cause a general purpose or special purpose processor, which is programmed with the instructions to perform the steps of an example embodiment. Alternatively, the features or steps may be performed by specific hardware components that contain hard-wired logic for performing the steps, or by any combination of programmed computer components and custom hardware components. While embodiments are described with reference to the Internet, the method and apparatus described herein is equally applicable to other network infrastructures or other data communications systems.
Various embodiments are described. In particular, the use of embodiments with various types and formats of user interface presentations may be described. It can be apparent to those of ordinary skill in the art that alternative embodiments of the implementations described herein can be employed and still fall within the scope of the claimed invention. In the detail herein, various embodiments are described as implemented in computer-implemented processing logic denoted sometimes herein as the “Software”. As described above, however, the claimed invention is not limited to a purely software implementation.
Thus, a computer-implemented method and system for keyword bidding are disclosed. While the present invention has been described in terms of several example embodiments, those of ordinary skill in the art can recognize that the present invention is not limited to the embodiments described, but can be practiced with modification and alteration within the spirit and scope of the appended claims. The description herein is thus to be regarded as illustrative instead of limiting.
This patent application claims the benefit of the filing date of U.S. Provisional Patent Application Ser. No. 61/105,387, filed on Oct. 14, 2008, entitled, “A COMPUTER-IMPLEMENTED METHOD AND SYSTEM FOR KEYWORD BIDDING”, and assigned to the same assignee as the present patent application.
| Number | Date | Country | |
|---|---|---|---|
| 61105387 | Oct 2008 | US |
