Abstract: An advertising campaign has multiple objectives that the online system achieves by making appropriate bids for the advertising campaign. The online system presenting advertisement content modifies bid amounts associated with advertisements in the advertising campaign based on feedback about past performance of the advertising campaign. To satisfy the multiple objectives of the advertising campaign, the online system applies multiple mutually dependent pacing multipliers to determine and modify bid amounts of advertisements from the advertising campaign. One pacing multiplier is expressed in terms of the other pacing multiplier, and the online system modifies one pacing multiplier more frequently than the other pacing multiplier.

Abstract: An online system presenting content items to a user generates a model that predicts a latent metric describing user actions that occur at least a reasonable amount of time after presentation of content items. To determine the latent metric, the online system retrieves one or more models predicting likelihoods of the user performing various interactions when presented with the content items and determines weights associated with different retrieved models. Combining the weighted retrieved models generates a model for determining the latent metric. As the retrieved models are based on data accessible to the online system in less than the reasonable amount of time after presenting content items, weighing the retrieved models allows the online system to predict the latent metric describing user actions occurring after content items are presented. When selecting content items for the user, the online system accounts for the latent metric determined by the generated model.

Abstract: An online system receives a sponsored content item including a maximum amount of compensation for accessing the content, a budget, and a tracking mechanism identifying an action. When an opportunity to present sponsored content to a user eligible to be presented with the sponsored content item is identified, the online system determines a likelihood of the user performing the action identified by the tracking mechanism and an average likelihood of other users performing the action identified by the tracking mechanism. Based on the determined likelihood and the average likelihood, the online system determines a subsidy value. Additionally, the online system generates a penalty value inversely proportional to a number of the identified action that have been identified. The online system increases a bid amount by the subsidy value decreases the bid amount by the penalty value to determine whether to present the sponsored content item to the user.

Abstract: An online system receives a set of parameters for an advertising campaign and modifies one or more of the parameters to determine how the modified parameters affect presentation of advertisements from the advertising campaign. For example, the online system increases bid amounts or a budget for the advertising campaign for a number of impression opportunities for advertisements form the advertising system. The online system subsidizes the increase so a user providing the advertisement request is not charged extra for the increased bid amounts or budget. To offset potential benefits to the advertising campaign from the modified parameters, the online system withholds the advertising campaign from being considered for a certain number of impression opportunities for which the advertising campaign would otherwise be eligible.

Abstract: An online system caps an average amount of subsidy that an ad would receive during the duration of an ad campaign to an average bid price of the ad multiplied by an advertiser subsidy coefficient chosen by the advertiser. For a given impression opportunity, the online system determines a bid price, a user subsidy, and an aggregated subsidy coefficient for an ad. The online system determines the bid price for the ad based on the delivery parameters associated with the ad campaign. The online system determines a user subsidy for the ad based on user interactions with the ad. Furthermore, the online system determines the aggregated subsidy coefficient for the ad based on a ratio between an aggregated subsidy and an aggregated bid price. The amount of subsidy that online system provides to the ad is the user subsidy multiplied by the aggregated subsidy coefficient.

Abstract: An advertising campaign received by an online system has a specified budget, a specified duration, and includes multiple advertisement requests that each include advertisements for presentation to users of the online system. An ad request included in the advertising campaign is associated with a frequency limit specifying a maximum number of times an advertisement from the ad request is shown to a user during the specified duration. When selecting advertisements for presentation to a user, the online system determines an adjustment value for the ad request's bid amount based on a number of times the advertisement from the ad request has been presented to the user, an amount of the duration that has lapsed, and the frequency limit associated with the ad request. The online system modifies the ad request's bid amount by the adjustment value and uses the modified bid amount when selecting advertisements for presentation to the user.

Abstract: An advertising (“ad”) system allows users to specify a budget for an advertisement (“ad”) campaign including ad requests (“ads”), and the ad system automatically determines bids on a per-impression basis to pace the ad spend according to the budget. The ad system computes a “regret” metric for the ad campaign, which is the total amount over the course of the ad campaign that the advertiser had to pay for presenting an ad above the ideal bid (e.g., the bid that would have captured at least a threshold number of the lowest priced impressions during the ad campaign's life while spending the budget). The ad system may use the regret metric to indicate the performance of the ad campaign, e.g., as feedback for the advertiser.

Abstract: An online system applies advertising policies regulating presentation of sponsored content to its users. For example, advertising policies may prevent the presentation of advertisements in certain positions content feeds. The online system may relax an advertising policy for an advertisement meeting certain criteria, such as a likelihood of a user interacting with the advertisement or a predicted value of presenting the advertisement. If the online system relaxes an advertising policy for an advertisement, the online system computes a penalty incurred by the advertisement for violating the advertising policy. The online system computes a value for presenting a candidate feed presenting the advertisement in a position violating the advertising policy and a value for an alternative feed presenting the advertisement in a position complying with the advertising policy. The online system selects the candidate feed or the alternative feed for presentation to the user by comparing the values.

Abstract: A social networking system provides content items to a user via a feed that may include one or more sponsored content items. Multiple sponsored content items may be included in a set that is presented in the feed via a scrollable content unit that presents a sponsored content item from the set and presents additional sponsored content items from the set when user interaction is received. To place sponsored content items in the feed, the social networking system scores a set of sponsored content items based on prior user interactions with content presented via scrollable content units and a bid amount of a sponsored content item in the set. The set of sponsored content items is ranked among other sponsored content items based on its score. If the set of sponsored content items is selected for inclusion in the feed, the social networking system orders the sponsored content items in the set for presentation via the scrollable content unit.

Abstract: A social networking system presents a content feed including organic content items and sponsored content items to a user. To maintain user interaction with the content feed, the social networking system determines probabilities of the user performing various types of interactions with a sponsored content item and accounts for the determined probabilities when selecting content items for presentation via the content feed. For example, the social networking system generates a value for the sponsored content item based on the determined probabilities and determines a score for the sponsored content item based on the value and a bid amount associated with the sponsored content item. When selecting content for the content feed, the social networking system evaluates the sponsored content item based on its associated score. Prior interactions between the user and previously presented content may be used when determining the score for the sponsored content item.

Abstract: For ad campaigns including multiple advertisement (“ad”) requests each including an ad creative, which are automatically selected, a social networking system, or any other suitable online system, may bias selection of ad requests from an ad campaign towards early-selected ad requests with positive user interactions, limiting the number of ad requests selected from the ad campaign. To increase the likelihood of various advertisements in an ad campaign being evaluated for presentation to users, the social networking system modifies bid amounts associated with advertisements in the ad campaign using advertisement-specific bid adjustments based on interactions with the ad requests. Based on the modified bid amounts, the social networking system selects ad requests from the ad campaign to evaluate for presentation to a user.

Abstract: For an advertisement (“ad”) campaign including multiple ad requests, an advertiser may request presentation of a variety of ad requests in the ad campaign as well as specify an objective to be completed by the ad campaign during a time interval and subject to a budget. An online system presenting advertisement content may modify bid amounts associated with ad requests in the ad campaign using advertisement-specific bid adjustment values to select a more diverse range of ad requests from the ad campaign. To satisfy the objective without exceeding the budget, the online system also applies a pacing multiplier to bid amounts of ad requests selected from the ad campaign. As ad requests from the ad campaign are presented, the online system modifies the ad request-specific bid amounts and the pacing multiplier at different rates.

Abstract: An online system penalizes content items having features matching features of additional content items previously presented to a user within a specified time interval. The online system identifies various features of the content item and identifies features of content items previously presented to the user within the specified time interval. Feature penalties are determined for various features of the content item based on a number of previously presented content items having a common feature with the content item. Weights may be associated with various content items having a feature matching a feature of the content item based on a time between presentation of the previously presented content item and a current time. A penalty for the content item is determined based on the feature penalties for the features of the content item, and the penalty is applied to a bid amount associated with the content item.

Abstract: A social networking system presents content items, such as news feed stories and advertisements, to a user of the social networking system via a news feed. The social networking system determines to again present a content item via the news feed or to present a previously presented content item in a different position of the news feed. The social networking system identifies additional content items to present to the user as well as content items previously presented to the user. The social networking system scores the additional content items and the previously presented content items, accounting for a cost of removing the previously presented content item from its original position for presentation in the alternative position. Based on the score the social networking system ranks the content items selects, based on the rank, content items to present to the user.