Keyword bids determined from sparse data are described. Initially, a portfolio optimization platform identifies which keywords included in a portfolio of keywords are low-impression keywords. This platform trains a machine learning model to generate bids for the low-impression keywords with historical data from a search engine. In particular, the platform trains this machine learning model according to an algorithm suited for training with sparse amounts of data, e.g., a temporal difference learning algorithm. In contrast, the platform uses different models, trained according to different algorithms than the low-impression keyword model, to generate bids for keywords determined not to be low-impression keywords. Once the low-impression keyword model is trained offline, the platform deploys the model for use online to generate actual bids for the low-impression keywords and submits them to the search engine. The platform continues to update the low-impression keyword model while deployed according to the sparse-data algorithm.

An approach for creating dynamic content. The approach receives advertiser data associated with activities of one or more advertisers and receives publisher data associated with activities of one or more publishers. The approach manages the one or more DSPs activities associated with the received advertiser data and publisher data. Furthermore, the approach manages the one or more SSPs activities associated with the received advertiser data, publisher data and the one or more DSPs activities and selects one or more advertisement for one or more website. Finally, the approach manages the one or more consumer behaviors associated with the selected one or more advertisement.

A computer-implemented method for improved ticket purchasing/selling process using a ticketing system. The purchasing process of tickets for a user can be facilitated by a web interface having an event selection menu configured to display one or more events having tickets available for purchase. Available inventories for tickets to one or more events can be displayed on an interactive venue map of the web interface. The user can choose desired seats for purchase via the venue map. Additional menus can facilitate the ability for a user to compare show dates, showtimes, and seating availability across different events. The ticketing system can also be configured to collect and process customer data through tracking pixels configured within the one or more pages of the web interface. Subsequently, bidding on digital marketing and advertisement can be conducted using the gathered customer data.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for managing application program interface calls.

A system and process allowing for online participation in multiple simultaneous live auctions comprising an auction management system providing an advantageous user display enabling concurrent auction participation.

Within an advertising buying platform, advertising buyers are able to direct advertising content to TV/OTT/VOD inventory that matches targeted market segments. The advertising buyers select from a list of available market segments, and the system pairs the market segments to an anonymous dataset of media consumers (using a database of hashed online IDs). The dataset of hashed online IDs is then mapped to external OEM IDs (such as from a Smart TV) via the functions of a hashed identity mapping method. This permits the advertiser to target advertising content to a population of TV viewers. Also described herein are methods of bidding on programmatic TV content.

Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing a program and method for selecting ads for a video. The program and method provide for receiving a request for an ad to insert into a video playing on a client device, the request including a first content identifier that identifies a first type of content included in the video; determining a set of content identifiers associated with the first content identifier, the set of content identifiers identifying second types of content to filter with respect to providing the ad in response to the request; selecting an ad from among plural ads, by filtering ads tagged with a second content identifier included in the set of content identifiers; and providing the selected ad as a response to the request.

A method and system for controlling real-time bidding for online advertisements is disclosed. According to one embodiment, a computer-implemented method comprises communicating with a bidder and an impression server and an event tracking server. The bidder receives a real-time bidding (RTB) request containing an available impression from an exchange and places a bid corresponding to the RTB request. The impression server receives impression requests from a browser and responds to the impression requests from the browser. The event tracking server receives event requests from the browser and responds to event requests from the browser. Campaign performance data is retrieved from one or more of the impression server and the event tracking server and compared to the campaign target. The bidder is notified whether to bid for online advertisement impressions based on the campaign performance data.

A system and methods are disclosed for scoring audience responsiveness or exposure to viewing of paid content or advertising via connected television devices (CTV) and/or over-the-top (OTT) delivery mechanisms. The scoring system and method determines relevant data and creates and records the relevant data in an Ad Exposure File and an Advertiser Outcome File and at regular intervals compares them to identify matches via overlapping combinations of IP Address/DID, Timestamp (for confirmation of appropriate recency) and recording a conversion event to the Exposed Household Record. of the appropriate household on the Ad Exposure File.

A media presentation and distribution system includes a verification server that handles dynamic verification of playback of media assets on a client device. The client device generates support information for a media asset based on an associated asset identifier that is detected during a playback of the media asset on a client device. The client device further encrypts the support information for the media asset based on a client private key associated with the client device and an asset public key for the media asset. The playback of the media asset on the client device is verified based on a verification message, the support information, an encrypted verification message, and the associated asset identifier. A defined asset delivery criteria is satisfied and a deviation or an error with the playback of the media asset is identified based on the verification of the playback of the media asset.