Abstract: A method and system provide the ability to forecast events that match a criterion. Input is received and includes an event set and a criterion. The event set includes events and each of the events is a record with features. Each feature is an instance of a feature type (FT) and feature value (FV) combination. The criterion is a logical statement that specifies a criterion FT, a criterion FV, and an operator. The event set is partitioned and a partition BitSet is built for each partition. Each partition length of each partition BitSet is based on a number of the events. Based on the partition BitSets, a partition FT-FV count is created. For each partition, a partition FT criterion BitSet is created and a partition Criterion BitSet is computed based thereon. The forecast is then computed based on the partition Criterion BitSet.

Abstract: A method and system provide the ability to determine matching subjects for features provided in a stimulus. Subject information is pre-processed by receiving input (a feature type definition and a subject set) and building BitSets across all subjects in the subject set. The stimulus is received and includes stimulus features. For each feature type in the stimulus features, all feature type BitSets from the subject set that match are assembled. An evaluation BitSet is built by combining the assembled feature type BitSets. Matching subjects that match the stimulus are determined based on the evaluation BitSet.

Abstract: A method and system provide the ability to forecast events that match a criterion. Input is received and includes an event set and a criterion. The event set includes events and each of the events is a record with features. Each feature is an instance of a feature type (FT) and feature value (FV) combination. The criterion is a logical statement that specifies a criterion FT, a criterion FV, and an operator. The event set is partitioned and a partition BitSet is built for each partition. Each partition length of each partition BitSet is based on a number of the events. Based on the partition BitSets, a partition FT-FV count is created. For each partition, a partition FT criterion BitSet is created and a partition Criterion BitSet is computed based thereon. The forecast is then computed based on the partition Criterion BitSet.

Abstract: A method and system provide the ability to determine matching subjects for features provided in a stimulus. Subject information is pre-processed by receiving input (a feature type definition and a subject set) and building BitSets across all subjects in the subject set. The stimulus is received and includes stimulus features. For each feature type in the stimulus features, all feature type BitSets from the subject set that match are assembled. An evaluation BitSet is built by combining the assembled feature type BitSets. Matching subjects that match the stimulus are determined based on the evaluation BitSet.

Abstract: A method, system, apparatus, advertising exchange system, and computer program product for acquiring advertisement impressions through an advertisement auction. A first maximum bid price to acquire an impression is defined. An entity set of one or more entities is identified. A second maximum bid price (that is higher than the first maximum price) to acquire the impression is defined. The first max bid price is used to bid for the impression during the advertisement auction. If the auction is being lost to the entity set, the bidding continues using the second maximum bid price.

Abstract: A method, apparatus, system, and computer program product provide the ability to bid for an advertising impression. Within an advertising exchange, an advertising bidding impression campaign to bid for the advertising impression is initialized. A desired impression quality rank is selected and a bid against the desired rank is accepted. An actual impression quality rank for an actual advertising impression in an advertising impression inventory is determined. Based on the bid and the actual impression quality rank, the actual advertising impression is awarded to the bidder.