Abstract: Technology for predicting online user shopping behavior, such as whether a user will purchase a product, is described. An example method includes receiving current session data describing a current session for a current user, extracting a current clickstream from the current session data classifying the current clickstream as a purchase clickstream or a non-purchase clickstream by processing the current clickstream using one or more sets of Hidden Markov Model parameters produced by one or more Hidden Markov Models, and computing, using the one or more computing devices, a purchase probability that the current user will purchase a product during the current session based on the classifying.

Abstract: Technology for determining the order of the search results to maximize a financial goal is described. In an example embodiment, a method, implemented using the one or more computing devices, such as client and/or server devices, may receive a product search request from a user device associated with a user and retrieve a set of products from a product database based on the product search request. Based on a purchase probability and one or more of a margin and a price for that product, the method determines an expected financial gain for each of the products of the set and sorts the set of products into an ordered set of products having an order based on the expected financial gain associated with each of the products. The method may then provide the ordered set of products for display to the user on the user device.

Abstract: Technology for determining an optimal discounted price for a customer for a particular product is described. In an example embodiment, a method comprises determining a number of visits to a product page of a particular product by customers, calculating a purchase probability of a customer to purchase the particular product associated with the product page as a function of a price discount, determining a discount-corrected margin specific to the customer for the particular product based on the purchase probability of the customer, and calculating a predicted profit or a predicted revenue for the particular product resulting from the number of visits to the product page and based on the purchase probability and the discount-corrected margin of the particular product.

Abstract: Technology for predicting online user shopping behavior, such as whether a user will purchase a product, is described. An example method includes receiving current session data describing a current session for a current user, extracting a current clickstream from the current session data classifying the current clickstream as a purchase clickstream or a non-purchase clickstream by processing the current clickstream using one or more sets of Hidden Markov Model parameters produced by one or more Hidden Markov Models, and computing, using the one or more computing devices, a purchase probability that the current user will purchase a product during the current session based on the classifying.

Abstract: Various embodiments pertain to serving a number of advertisements in view of browser information and a user's interaction with the web page containing the advertisements. In at least some embodiments, information regarding the size of a browser user interface in which a browser renders the web page, visibility of the browser user interface, or status of the browser can be obtained and utilized to determine a number of slots available for advertisements. For example, if a browser is being used to render a web page on a screen of a mobile device, fewer advertisements can be served compared to when the same web page is rendered by a browser on a desktop monitor. In some embodiments, page script can be used to obtain information regarding the size of a browser user interface, visibility of the browser user interface, or status of the browser.

Abstract: Various embodiments pertain to serving a number of advertisements in view of browser information and a user's interaction with the web page containing the advertisements. In at least some embodiments, information regarding the size of a browser user interface in which a browser renders the web page, visibility of the browser user interface, or status of the browser can be obtained and utilized to determine a number of slots available for advertisements. For example, if a browser is being used to render a web page on a screen of a mobile device, fewer advertisements can be served compared to when the same web page is rendered by a browser on a desktop monitor. In some embodiments, page script can be used to obtain information regarding the size of a browser user interface, visibility of the browser user interface, or status of the browser.

Abstract: Computer-readable media and a computer system for correcting bid estimates that are calculated from stored data encompassing an incumbent customer's participation in a keyword auction are provided. Initially, input criteria is received, which includes customer-history data and a candidate position, within a ranking of incumbent customers competing to display an advertisement, that is attractive to the incumbent customer. A corrected rank model of the competing incumbent customers' ranking is generated, which effectively discounts the stored data related to the incumbent content provider. The corrected rank model is utilized to predict an adjusted average position of the incumbent content provider, within the ranking of the competing incumbent customers, without physically extracting stored data associated therewith. A corrected price model that ignores the influence of the incumbent customer's participation in the advertising auction is then constructed.

Abstract: Systems and methods for identifying monetization values for voice-enabled text advertisements and for providing the voice-enabled text advertisements for presentation to users within electronic advertising environments are provided. Advertisers may submit bids on both text advertisements and voice-enabled text advertisements. Using the bids submitted by advertisers, monetization values for text advertisements and voice-enabled text advertisements are calculated. The monetization values for voice-enabled text advertisements may be calculated based on a cost-per-voice bid submitted by the advertiser indicating a monetary amount the advertiser is willing to pay for voice audio of the voice-enabled text advertisement. Based on the monetization value of each of the voice-enabled text advertisements, at least one voice-enabled text advertisement is selected for presentation. The selected voice-enabled text advertisement is communicated for presentation to the user.

Abstract: Methods are provided for determining a customized voice to be used for an audio advertisement. Text of an advertisement is received, and it is determined that audio is to be generated from the text of the advertisement, and that the audio is to comprise a customized voice. The customized voice is selected by the advertiser. The audio is generated from the text of the advertisement, and the text, audio, and indications that the advertisement is voice-enabled and that a customized voice is to be used in association with the audio are stored in an advertisement storage. When a request is received for advertisements, at least one advertisement is communicated for presentation to the user, such that the text is visually presented to the user and audio comprising the customized voice is audibly presented to the user.

Abstract: Methods, systems, and computer storage media having computer-executable instructions embodied thereon that, when executed, perform methods for determining bid amounts necessary to ensure advertisements or other content items will be presented in designated positions other than the most prominent (or first) position when bid information associated with a lesser included match type is not requested, are provided. Bids are received that are associated with a given keyword, a content item and a desired placement position. Based thereupon, a placement position in which the bid will cause associated content item is determined and compared to the desired placement position. If the determined placement position is not within a given error threshold of the desired placement position, the bid is iteratively adjusted in such a way that an adjusted bid amount is determined which will ensure placement in the desired position.

Abstract: In this invention, systems and methods for providing a price estimate for two or more keywords are provided. More specifically, a price estimate is determined and provided when each keyword has terms in common, where each keyword includes one or more terms. For example, a first keyword (e.g., “car”) and a second keyword (e.g., “new car”) share a common word. Thus, the price estimate of these keywords will factor in the commonality between the keywords and provide a more accurate price estimate to the advertiser, when bidding on the keywords. A more accurate price estimate allows the advertiser to better estimate their advertising budget when factoring in the overlapping keyword traffic, and accordingly, bid on more keywords.

Abstract: In this invention, systems and methods for providing a price estimate for two or more keywords are provided. More specifically, a price estimate is determined and provided when each keyword has terms in common, where each keyword includes one or more terms. For example, a first keyword (e.g., “car”) and a second keyword (e.g., “new car”) share a common word. Thus, the price estimate of these keywords will illuminate the overlapping traffic between the keywords and provide a more accurate price estimate to the advertiser, when bidding on the keywords. A more accurate price estimate allows the advertiser to better estimate their advertising budget when factoring in the overlapping keyword traffic, and accordingly, bid on more keywords.

Abstract: Computer-readable media and a computer system for correcting bid estimates that are calculated from stored data encompassing an incumbent customer's participation in a keyword auction are provided. Initially, input criteria is received, which includes customer-history data and a candidate position, within a ranking of incumbent customers competing to display an advertisement, that is attractive to the incumbent customer. A corrected rank model of the competing incumbent customers' ranking is generated, which effectively discounts the stored data related to the incumbent content provider. The corrected rank model is utilized to predict an adjusted average position of the incumbent content provider, within the ranking of the competing incumbent customers, without physically extracting stored data associated therewith. A corrected price model that ignores the influence of the incumbent customer's participation in the advertising auction is then constructed.

Abstract: Methods, systems, and computer storage media having computer-executable instructions embodied thereon that, when executed, perform methods for determining bid amounts necessary to ensure advertisements or other content items will be presented in designated positions other than the most prominent (or first) position when bid information associated with a lesser included match type is not requested, are provided. Bids are received that are associated with a given keyword, a content item and a desired placement position. Based thereupon, a placement position in which the bid will cause associated content item is determined and compared to the desired placement position. If the determined placement position is not within a given error threshold of the desired placement position, the bid is iteratively adjusted in such a way that an adjusted bid amount is determined which will ensure placement in the desired position.