摘要:
Systems and methods are provided for predicting visitor traffic to a network of web site pages. The systems and methods are used, as an example, to predict the inventory of total available online advertisements available within the network for a forthcoming period. The visitor traffic includes page viewing, listening or transacting on web pages within a web site, wherein the web pages are categorized by subject, interest areas or specific user queries such as word or phrase searches. For each page whose traffic is being predicted, the system takes into account annual seasonality, day-of-week, holidays, special events, short histories, user demographics, user web behavior (viewing, listening and transacting) and parent and child web page characteristics.
摘要:
A method attributes credit for conversions to a plurality of event types. A plurality of probabilities that a single impression of each of a plurality of respective event types causes a conversion by one of a plurality of users are defined. A processor is used to select values for the plurality of probabilities so as to minimize a total squared error based on differences between an observed outcome for each user and a respective expected outcome for each user calculated from the plurality of probabilities.
摘要:
A method of balancing advertisement inventory allocation includes constructing a flow network of nodes having impressions connected to contracts through corresponding arcs such as to satisfy demand requests of the contracts; normalizing an impression value of each node to a predetermined cost range; setting a cost of each arc to each corresponding normalized value; iteratively performing a plurality of times: (a) sampling the nodes or the arcs to create sample nodes and arcs, each time starting from a different random seed; (b) optimally allocating impressions from the sample nodes to the contracts with a minimum-cost network flow algorithm; (c) separately allocating impressions from sample arcs of lowest cost before allocating those from sample arcs of higher cost; averaging allocations from iterations (b) to create a first allocation; averaging allocations from iterations (c) to produce a second allocation; and computing a weighted solution of the first and second allocations.
摘要:
A system for advertisement inventory allocation is disclosed, including a database to store advertisement impressions. An indexer builds a plurality of index tables each associated with an attribute that is mapped to a plurality of the impressions. An impression matcher constructs a flow network including a plurality of nodes each containing impressions of at least one corresponding attribute projected to be available during a time period, a plurality of contracts each including specific requests for impressions that satisfy a demand profile during the time period, and a plurality of arcs to connect the plurality of nodes to the plurality of contracts that match the demand profile of each contract. An optimizer optimally allocates impressions from the nodes to the contracts during the time period by solving the flow network with a minimum-cost network flow algorithm that maximizes delivery of the impressions to the contracts in a way that satisfies the corresponding demand profiles and that specifies a number of impressions to flow over each of the plurality of arcs.
摘要:
A behavioral targeting system determines user profiles from online activity. The system includes a plurality of models that define parameters for determining a user profile score. Event information, which comprises on-line activity of the user, is received at an entity. To generate a user profile score, a model is selected. The model comprises recency, intensity and frequency dimension parameters. The behavioral targeting system generates a user profile score for a target objective, such as brand advertising or direct response advertising. The parameters from the model are applied to generate the user profile score in a category. The behavioral targeting system has application for use in ad serving to on-line users.
摘要:
A method and apparatus for selecting additional content to display to a user when the user requests base content is provided. A user profile of the user having user interest scores of categories or keywords is received, each user interest score reflecting the degree of interest the user has in the category or keyword. Performance scores reflecting the probability that a user having particular user interest scores will select additional content associated with particular categories or keywords is also received. In addition, revenue amounts associated with each category or keyword of the user profile is received. The user interest scores, performance scores, and revenue amounts are used to produce an expected revenue amount for each category or keyword in the user profile. Additional content to be sent to the user is then selected using the determined expected revenue amounts.
摘要:
A method attributes credit for conversions to a plurality of event types. A plurality of probabilities that a single impression of each of a plurality of respective event types causes a conversion by one of a plurality of users are defined. A processor is used to select values for the plurality of probabilities so as to minimize a total squared error based on differences between an observed outcome for each user and a respective expected outcome for each user calculated from the plurality of probabilities.
摘要:
An improved system and method for granular inventory forecasting of online advertisement impressions is provided. An impression forecast data integrator may be provided that generates forecasted impression pools of advertisements by integrating impression pools of advertisements that share the same attributes and trend forecast data for web pages and advertisement placements on the web pages. Using the trend forecast data, an inventory forecast for a category may be calculated and an inventory forecast for an impression pool may be calculated. A daily forecasted inventory may then be produced for each impression pool by minimizing an objective function of squared errors of the difference between the daily forecasted inventory for each category and the sum of the daily forecasted inventory for each impression pool. The daily inventory forecast for each pool may be output.
摘要:
A method for scaling advertisement inventory allocation includes constructing a flow network of nodes having impressions connected to contracts through corresponding arcs such as to satisfy demand requests of the contracts; (a) for each of the contracts: determining a probability distribution over the nodes eligible to supply forecasted impressions to the contract; drawing a plurality of sample nodes from the probability distribution to form a multiset, O, of nodes; (b) for each of the nodes within O: determining a subset of the contracts, H, that can be satisfied by receiving forecasted impressions from the node; weighting a number of forecasted impressions of the node, as a function of the subset of contracts in H, with the probability distribution of the node; and optimally allocating forecasted impressions from each multiset, O, of sample nodes to each corresponding contract during the time period by solving the flow network with a minimum-cost network flow algorithm.
摘要:
A method for scaling inventory allocation includes mapping attributes to impressions through index tables; constructing a flow network of nodes each containing impressions of corresponding attributes projected to be available during a time period, contracts each including specific requests for impressions that satisfy a demand profile, and arcs to connect the nodes to the contracts that match the demand profiles of the contracts; sampling the arcs that flow into each contract at a sampling rate chosen to reduce the number of arcs to a fraction of the original arcs when the plurality of impressions that satisfy the contract is above a threshold number, the nodes corresponding to the sampled arcs being sampled nodes; and optimally allocating impressions from the sampled nodes to the contracts during the time period by solving the flow network with a minimum-cost network flow algorithm that maximizes delivery of the impressions from the sampled nodes to the contracts in a way that satisfies the corresponding demand profiles.