An online system obtains risk scores determined by a machine learning model for a content item provided by a user of an online system for display to users of the online system, where the risk scores indicate the likelihood of content items violating a content policy. The online system uses the risk scores to determine sampling weights used to select content items for inclusion in a sampled subset of content items. The sampling weights are determined from risk score counts indicating the relative frequency of the obtained risk scores and impression counts indicating the number of times content items have been presented to the users of the online system. The online system presents the selected content items for evaluation by a human reviewer using a quality review interface. Using the results of the quality review, the online system determines quality performance metrics of the machine learning model.

A user targeted advertisement delivery system for delivering one or more targeted advertisements to the user is provided. The system includes a parking server that receives the user parking related information from the user device and one or more advertisements from the one or more advertiser devices. The parking server identifies and serves one or more targeted advertisements based on a location of parking, a time of day, a day of week, a calendar, and a duration of parking. The parking server communicates a notification (e.g., a parking receipt, reminders for timer expiry, thank you note once the time is over) along with one or more targeted advertisements to the user device when the user initiates a parking timer after parking his/her vehicle in a parking slot.

A computer system for providing digital advertiser referrals comprising a third party referral provider operable to maintain a store of digital referral objects, each digital referral object associated with an advertiser for referral to a consumer. The third party referral provider being further operable to engage with a consumer while the consumer is accessing digital content on a publisher site subscribing to the third party referral provider by way of a computer presentation interface, such that once the consumer has engaged with the third party referral provider, the third party referral provider is operable to refer one or more of the advertisers to the consumer through presentation of an associated digital referral object on the presentation interface.

A clustering and recommendation machine determines that an item is included in a cluster of items. The machine accesses item data descriptive of the item. The machine accesses a vector that represents the cluster and calculates the likelihood that the item is included in the cluster, based on the item variable and the probability parameter. The machine determines that the item is included in the cluster, based on the likelihood. The machine also recommends an item to a potential buyer. The machine accesses behavior data that represents a first event type pertinent to a first cluster of items. The machine calculates a probability that a second event type pertaining to a second cluster of items will co-occur with the first event type. The machine identifies an item from the second cluster to be recommended and presents a recommendation of the item to the potential buyer.

A system and method are disclosed for providing a promotion associated with a transaction account. Target viewer information associated with at least one person targeted to receive an ad is identified. In accordance with the target viewer information and the ad, a probability of the at least one person to accept the promotion is determined. Promotion information associated with the promotion is selected as a function of the determined probability, and the promotion information is transmitted to a computing device associated with the at least one person. An acceptance of the promotion is received from the computing device associated with the at least one person, and processed to associate the promotion with the transaction account.

The present invention pertains to assisting efficient sales activities at a financial institution by accurately extracting customers who are likely to need prescribed financial products. A sales assistance department according to the present invention has: an acquisition part for acquiring transaction data of customers at a financial institution; a relevance determination part for determining whether first transaction data of the customers at the past time of purchasing financial products relates to second transaction data of the customers at the current time; an extraction part for extracting a customer for whom it is determined that the first transaction data relates to the second transaction data; and an output part for performing output regarding the extracted customer.

The AUTOMATED ADVERTISING AGENCY APPARATUSES, METHODS AND SYSTEMS (“AAA”) provides a platform that, in various embodiments, is configurable to provide advertisement generation and/or placement facilities leveraging real-time or near real-time updating of social media data. The AAA may be configured to automatically direct advertising purchasing, configuration and placement, guide marketing efforts, and implement marketing strategies maximizing target impact. The AAA may further be configurable to forecast financial data, such as revenues, associated with queried products or services, and to direct optimized advertising configuration, purchasing and/or placement.

A method to control advertising messages directed at a user is provided. Such control might include setting a filter to control advertisements directed at a user. Advertisements are sent to a user based on the filter settings. The user may accept the advertisements. If the user accepts the advertisements, the user is provided with a reward. In addition, a method using a quiz to determine if a user is human or an automated respondent is provided. The user is presented with a quiz. The user is advised of the acceptable manner for responding to the quiz. The user's response to the quiz is received. A determination based on the user's response as to whether the user is a human or an automated respondent is made.

Provided is a process, including: obtaining a first training dataset, training a first machine-learning model on the first training dataset, obtaining a set of candidate question sequences, forming virtual subject-entity records, forming a second training dataset, training a second machine-learning model, and storing the adjusted parameters of the second machine-learning model in memory.

A system and methods for management and delivery of content and rules is disclosed. An exemplary method may comprise managing, for an organization, a plurality of data and a plurality of content in separate database entities, wherein the plurality of content is associated with the plurality of data based on a plurality of rules; packaging the plurality of rules with the plurality of content in a carrier that is independent from one or more presentation channels, wherein at least part of the plurality of content is integrated with at least part of the plurality of data; delivering the plurality of data and the carrier to the one or more presentation channels; integrating, at the one or more presentation channels, the plurality of data with the plurality of content based on the plurality of rules; and distributing the integrated data and content through the one or more presentation channels.