Keyword - A Magical Tool

The keyword positions to aim for on search engines using users’ navigation histories accessible to advertisers. The navigation history of users who interacted with an element of a campaign is represented by a flow in a graph. We use formulas that link changes in keyword positions with the number of clicks on the ads whose appearance was triggered by those keywords, and show how these changes modify the flow. Taking into account budget constraints, we then describe algorithms that reorganize the flow by changing keyword positions to maximize the expected profit from conversions tracked online.

???The importance of keywords in SEO was investigated as a major factor. Thorough incorporation of other problems that a website undoubtedly has, however, has already begun to apply for an overall modeling representation of SEO strategies and their advantages as the chaotic mantle of search engine results looms.

???????On search engines, after a user types a request in the search field, the auction takes place during the loading of the page. Each search engine has a set of criteria to rank the applied ads. According to AdWords [1, 2] and Bing Ads [4], the most common criteria are the maximum cost-per-click (i.e., the maximal amount the advertiser is ready to pay for each click on his ad), the ad relevance, and its past performance. The higher an ad is ranked (i.eThe closest it is to position 1), the more people click on it, and the more expensive each click will be. The first links an ad position and the average cost-per-click billed to the advertiser; The second link the ad position and the number of clicks on the said ad. The tool to help advertisers identify which elements of their campaigns contributed the most to their goals using navigation histories of users who interacted with at least one element of their campaigns.

Those elements are:

? Search queries: texts typed by users in the search field of the search engine;

? Keyword/ad pairs: any given keyword can trigger the impression of multiple ads and the impression of any given ad can be triggered by more than one keyword. In this work, we aggregate a keyword to each ad and which impression it triggered in a pair.

? Banners: display ads published on a third-party website i.e. that is neither the advertiser’s website nor a search engine;

? Conversions: a conversion happens when someone clicks on an ad and then takes an action that the advertiser has defined as valuable to his business, such as an online purchase or a call to his business from a mobile phone;

? Pages of the advertiser’s website: only those that are tagged.

The effectiveness of a marketing campaign depends on many factors. The focus is on the keyword positions to maximize profitability under budget constraints. The algorithms that determine which position to assign to each keyword in a search campaign of an advertiser.

???To establish links between the elements of the campaigns of a given advertiser, the users’ navigation histories are represented by a flow in a graph where each vertex represents one element, and an arc links two elements if and only if the first preceded the second in at least one of the users’ histories. The model takes into account the change in the average cost-per-click as well as changes in users’ behavior related to the changes in keyword positions. To evaluate the consequences of those changes on the rest of the campaigns, once the position is set for each keyword, the expected flow changes on the vertices representing the keywords are propagated through the network.

????In digital advertising, many companies are focused on the point of view of Internet companies such as Google and Microsoft and were written by people working for those companies. Even though that might help understand better how such companies manage the ad auctions, advisers do not have access to the required data and cannot use those words directly to improve the effectiveness of their digital campaigns.?