Analyzing auction data having a varying number of bidders

A method, comprising:

• organizing previously acquired auction data into a plurality of sub-samples, each sub-sample comprising bid data associated with auctions having a common number of bidders, a first sub-sample comprising bid data associated with auctions having more bidders than all other sub-samples;
• applying an inverse bid function to the largest sub-sample to produce initial pseudo values;
• applying a direct bid function to the initial pseudo values to calculate sample bids associated with a second sub-sample that is the next largest sub-sample, in terms of number of bidders, after the first sub-sample;
• matching bid data contained in the second sub-sample with the sample bids to produce second pseudo values;
• and
• combining the first and second pseudo values together to produce combined auction values.

A system, comprising:

• a processor;
• memory containing an auction application that is executed by the processor and causes the processor to
• form a plurality of sub-samples from an auction data set, each sub-sample comprising bid data associated with auctions having a common number of bidders;
• apply an inverse bid function to at least two sub-samples;
• aggregate results from applying the inverse bid function to form a first pool;
• apply a direct bid function on the first pool to generate sample bids;
• match bids from at least one sub-sample to the sample bids;
• and
• aggregate results from the matching with the first pool to form a second pool.

A system, comprising:

• a processor;
• an application executable by said processor and that causes the processor to
• organize previously acquired auction data into a plurality of sub-samples, each sub-sample comprising bid data associated with auctions having a common number of bidders;
• apply an inverse bid function to at least two sub-samples;
• re-sample results from applying the inverse bid function to generate re-sampled data;
• apply a direct bid function on the sampled data to generate sample bids;
• and
• match bids from at least one sub-sample to the sample bids.

A computer readable storage medium storing instructions that when executed by a processor cause the processor to process auction data, said instructions comprising:

• at least one instruction that organizes previously acquired auction data into a plurality of sub-samples, each sub-sample comprising bid data associated with auctions having a common number of bidders;
• at least one instruction that applies a first bid function to at least two sub-samples;
• at least one instruction that re-samples results from applying the first bid function to generate re-sampled data;
• at least one instruction that applies a second bid function on the sampled data to generate sample bids;
• and
• at least one instruction that matches bids from at least one sub-sample to the sample bids.

A computer readable storage medium storing instructions that when executed by a processor cause the processor to process auction data, said instructions comprising:

• at least one instruction that forms previously acquired auction data into a plurality of sub-samples, each sub-sample comprising auction data associated with auctions having a common number of bidders, a first sub-sample comprising bid data associated with auctions having more bidders than all other sub-samples;
• at least one instruction that applies an inverse bid function to the largest sub-sample to produce initial pseudo values;
• at least one instruction that applies a direct bid function to the initial pseudo values to calculate sample bids associated with a second sub-sample that is the next largest sub-sample, in terms of number of bidders, after the first sub-sample;
• at least one instruction that matches bid data contained in the second sub-sample with the sample bids to produce second pseudo values;
• and
• at least one instruction that combines the first and second pseudo values together to produce combined auction values.