Abstract: An advertising selection and placement system is provided for a social networking system. An advertising selection module identifies candidate advertisements for a user to view along with social networking content. The candidate advertisements can be placed in various slots on the user's display. The expected value of various arrangements of the candidate advertisements in the slots is determined, and advertisements may be selected and placed to optimize revenue to the system. Each advertisement is evaluated using a discount function that adjusts the price of the advertisement based on its placement.

Abstract: A social networking system presents advertisements and recommendation units to its users. The recommendation units suggest actions for the users to increase their engagement with the social networking system or otherwise interact with other users, while the social networking system receives revenue from advertisers for displaying advertisements based on bid values associated with the advertisements. The social networking system determines values for the advertisements and for the recommendation units, where the values are measured in a comparable fashion. This allows the system to rank and select the advertisements and recommendation units together in a unified auction model. For example, the social networking system uses a pacing value to determine values of recommendation units having a common unit of measurement with expected values of advertisements to the social networking system.

Abstract: A social networking system (SNS) provides sponsored stories and organic stories about actions taken by other SNS users to a viewing user. Organic stories are selected based on the likelihood the viewing user is interested in their content. While advertisers compensate the SNS for presentation of sponsored stories, the sponsored stories also include information about actions by other SNS users. To increase the likelihood the viewing user interacts with sponsored stories, a common communication channel is used to present both the sponsored stories and the organic stories. To simplify selection of organic stories and sponsored stories, the SNS determines a common unit of measurement for both and makes selections based on the common unit of measurement.

Abstract: A social networking system presents content items to users, who then provide feedback regarding pairs of content items. The feedback includes a selection of a content item of the pair of content items that was preferred by the user over the other content item. The social networking system uses this information to train a predictive model that scores content items based on quality. The content items may be advertisements. The social networking system uses the pair-wise comparisons of the advertisements to determine feedback coefficients in an advertising quality score prediction model using regression analysis of the pair-wise comparisons for each predictive factor in the model. In this way, the pair-wise comparisons are used to train the prediction model to understand which advertisements are more enjoyable than others. A feedback coefficient for each predictive factor may be computed based on the preferences received from the group of users.

Abstract: A social networking system presents content items to users, who then provide feedback regarding pairs of content items. The feedback includes a selection of a content item of the pair of content items that was preferred by the user over the other content item. The social networking system uses this information to train a predictive model that scores content items based on quality. The content items may be advertisements. The social networking system uses the pair-wise comparisons of the advertisements to determine feedback coefficients in an advertising quality score prediction model using regression analysis of the pair-wise comparisons for each predictive factor in the model. In this way, the pair-wise comparisons are used to train the prediction model to understand which advertisements are more enjoyable than others. A feedback coefficient for each predictive factor may be computed based on the preferences received from the group of users.

Abstract: A social networking system presents recommendation units to its users. The recommendation units suggest actions for the users to increase their engagement with the social networking system or otherwise interact with other users. The social networking system establishes internal goals and associates bids for recommendation units with different goals. The bids reflect the value to the goal of a user interacting with a recommendation unit. Based on bids for recommendation units associated with one or more goals, expected values of the recommendation units arid determined. The recommendation units are ranked based on the expected values and one or more recommendation units are selected based on the ranking.

Abstract: A social networking system presents content items to users, who then provide feedback regarding pairs of content items. The feedback includes a selection of a content item of the pair of content items that was preferred by the user over the other content item. The social networking system uses this information to train a predictive model that scores content items based on quality. The content items may be advertisements. The social networking system uses the pair-wise comparisons of the advertisements to determine feedback coefficients in an advertising quality score prediction model using regression analysis of the pair-wise comparisons for each predictive factor in the model. In this way, the pair-wise comparisons are used to train the prediction model to understand which advertisements are more enjoyable than others. A feedback coefficient for each predictive factor may be computed based on the preferences received from the group of users.

Abstract: A social networking system (SNS) provides sponsored stories and organic stories about actions taken by other SNS users to a viewing user. Organic stories are selected based on the likelihood the viewing user is interested in their content. While advertisers compensate the SNS for presentation of sponsored stories, the sponsored stories also include information about actions by other SNS users. To increase the likelihood the viewing user interacts with sponsored stories, a common communication channel is used to present both the sponsored stories and the organic stories. To simplify selection of organic stories and sponsored stories, the SNS determines a common unit of measurement for both and makes selections based on the common unit of measurement.

Abstract: A social networking system presents advertisements and recommendation units to its users. The recommendation units suggest actions for the users to increase their engagement with the social networking system or otherwise interact with other users, while the social networking system receives revenue from advertisers for displaying advertisements based on bid values associated with the advertisements. The social networking system determines values for the advertisements and for the recommendation units, where the values are measured in a comparable fashion. This allows the system to rank and select the advertisements and recommendation units together in a unified auction model. For example, the social networking system uses a pacing value to determine values of recommendation units having a common unit of measurement with expected values of advertisements to the social networking system.

Abstract: An advertising selection and placement system is provided for a social networking system. An advertising selection module identifies candidate advertisements for a user to view along with social networking content. The candidate advertisements can be placed in various slots on the user's display. The expected value of various arrangements of the candidate advertisements in the slots is determined, and advertisements may be selected and placed to optimize revenue to the system. Each advertisement is evaluated using a discount function that adjusts the price of the advertisement based on its placement.

Abstract: A social networking system selects advertisements for its users using collaborative filtering based on the users' interactions with objects in the social networking system. The objects may be games, pages, groups, deals, messages, content items, advertisements, or any other object with which a user may interact in the system. The system may identify a viewing user's interaction with a first object, determine a second object that is similar to the first object based on interactions of users with both of the objects, and send an advertisement associated with the second object to the viewing user. The system determines a second object based a similarity score between the first object and the second object, which may be a measure of users who have interacted with both objects and may be normalized by a number of user interactions by the users with the objects.

Abstract: A social networking system infers a user's present interests based on the user's recent actions and/or the recent actions of the user's connections in the social networking system. The social networking system also determines a set of concepts associated with each of a set of information items, such as advertisements. By matching the user's present interests with the concepts associated with the information items, the social networking system selects one or more of the information items that are likely to be of present interest to the user. At least one of the matched interests and concepts are not identical. The social networking system then presents the selected information items for display to the user, thereby providing information based on an inferred temporal relevance of that information to the user.

Abstract: An online advertising system receives ads from advertisers, which may also provide associated budgets, time period constraints, impressions goals, and performance weightings for the ads. When an ad is requesting from the advertising system from a client, a bid may be determined for each ad based on the budget associated the ad and/or the impressions goal associated with the ad. Ad performance associated with the ad request may be predicted, and a bid may be determined for each ad based on the performance weightings and the predicted performance associated with the ad request. The bid for an ad may be weighted by the pace of budget consumption by the ad, or by the pace of the ad progressing towards the ad's impression goal. An ad is selected for display to the client from among the one or more ads based on the determined bids for the ads.

Abstract: An online advertising system receives ads from advertisers, which may also provide associated budgets, time period constraints, impressions goals, and performance weightings for the ads. When an ad is requesting from the advertising system from a client, a bid may be determined for each ad based on the budget associated the ad and/or the impressions goal associated with the ad. Ad performance associated with the ad request may be predicted, and a bid may be determined for each ad based on the performance weightings and the predicted performance associated with the ad request. The bid for an ad may be weighted by the pace of budget consumption by the ad, or by the pace of the ad progressing towards the ad's impression goal. An ad is selected for display to the client from among the one or more ads based on the determined bids for the ads.

Abstract: Advertisements to be presented to a user are selected based on feedback responses received from other users where the feedback responses represent the level of interest to the advertisements expressed by the other users. In selecting which advertisements to be presented to a user, the online service takes into account feedback responses previously collected from a group of users and revenue expected for presenting certain advertisements to the user. An online service computing device computes a total value of an advertisement based on an estimated revenue value for presenting an advertisement and a modifier representing the user's estimated interest in the advertisements. The modifier is normalized based on a market value of the corresponding advertisement or a user. The online service then selects or prioritizes the advertisements based on the total values.

Abstract: A social networking system presents content items to users, who then provide feedback regarding pairs of content items. The feedback includes a selection of a content item of the pair of content items that was preferred by the user over the other content item. The social networking system uses this information to train a predictive model that scores content items based on quality. The content items may be advertisements. The social networking system uses the pair-wise comparisons of the advertisements to determine feedback coefficients in an advertising quality score prediction model using regression analysis of the pair-wise comparisons for each predictive factor in the model. In this way, the pair-wise comparisons are used to train the prediction model to understand which advertisements are more enjoyable than others. A feedback coefficient for each predictive factor may be computed based on the preferences received from the group of users.

Abstract: Advertisements to be presented to a user are selected based on feedback responses received from other users where the feedback responses represent the level of interest to the advertisements expressed by the other users. In selecting which advertisements to be presented to a user, the online service takes into account feedback responses previously collected from a group of users and revenue expected for presenting certain advertisements to the user. An online service computing device computes a total value of an advertisement based on an estimated revenue value for presenting an advertisement and a modifier representing the user's estimated interest in the advertisements. The online service then selects or prioritizes the advertisements based on the total values. Advertisements with more positive feedback responses and/or less negative feedback responses tend to have higher total values, and therefore, such advertisements are more likely to be selected for presentation to the users.