Bid value determination for a first-price auction
Shaded bid values may be determined and/or submitted to one or more auction modules for participation in auctions. Auction information including at least one of impression indications associated with the auctions, sets of features associated with the auctions, the shaded bid values associated with the auctions, etc. may be stored in a database. A machine learning model may be trained using the auction information to generate a first machine learning model with feature parameters associated with features. A bid request, indicative of a second set of features, may be received. The first machine learning model may be used to determine win probabilities and/or expected bid surpluses associated with multiple shaded bid values based upon one or more feature parameters, of the feature parameters, associated with the second set of features. A shaded bid value for submission may be determined based upon the win probabilities and/or the expected bid surpluses.
1. A method, comprising:
receiving, by a demand-side platform (DSP), a first bid request, wherein:
the first bid request is associated with a first request for content associated with a first client device; and
the first bid request is indicative of a first set of features comprising one or more first features associated with the first request for content;
determining, based upon a first bid value associated with a first content item, a first shaded bid value associated with the first content item;
submitting, by the DSP, the first shaded bid value to a first auction module, of a supply-side platform (SSP), for participation in a first auction associated with the first request for content;
receiving, by the DSP, a first impression indication indicative of whether the first content item is a winner of the first auction;
storing, in an auction information database, a first set of auction information associated with the first auction, wherein:
the first set of auction information is indicative of:
the first set of features;
the first impression indication; and
the first shaded bid value; and
the auction information database comprises a plurality of sets of auction information, comprising the first set of auction information, associated with a plurality of auctions comprising the first auction;
training a machine learning model using the plurality of sets of auction information to generate a first machine learning model comprising a plurality of feature parameters associated with a plurality of features of the plurality of sets of auction information;
loading the machine learning model onto a bid shading module of the DSP;
receiving, by the DSP, a second bid request, wherein:
the second bid request is associated with a second request for content associated with a second client device; and
the second bid request is indicative of a second set of features comprising one or more second features associated with the second request for content;
determining a second bid value associated with a second content item;
inputting, into the bid shading module of the DSP, the second bid value;
determining, based upon the second set of features and using the first machine learning model loaded onto the bid shading module of the DSP, a plurality of win probabilities associated with a plurality of shaded bid values, wherein:
each shaded bid value of the plurality of shaded bid values does not exceed the second bid value; and
a first win probability of the plurality of win probabilities is associated with a second shaded bid value of the plurality of shaded bid values and corresponds to a probability that the second content item wins an auction associated with the second request for content responsive to submitting the second shaded bid value to an auction module associated with the second request for content;
determining, based upon the plurality of win probabilities associated with the plurality of shaded bid values, a third shaded bid value; and
submitting the third shaded bid value to a second auction module for participation in a second auction associated with the second request for content,
wherein one or more content items are provided for presentation on the second client device associated with the second request for content based upon a determination that the one or more content items are a winner of the second auction.
2. The method of claim 1 , wherein:
the determining the plurality of win probabilities is performed based upon a set of feature parameters, of the plurality of feature parameters, associated with the second set of features.
3. The method of claim 2 , wherein:
a first feature parameter, of the set of feature parameters, is associated with a first feature of the second set of features; and
the first feature parameter comprises a first weight associated with the first feature.
4. The method of claim 3 , wherein:
the first machine learning model comprises a first bid parameter; and
the determining the plurality of win probabilities is performed based upon the first bid parameter.
5. The method of claim 4 , wherein:
the first machine learning model comprises a first bias parameter; and
the determining the plurality of win probabilities is performed based upon the first bias parameter.
6. The method of claim 5 , wherein:
the first bid parameter comprises a first bid weight; and
the first bias parameter comprises a first bias weight.
7. The method of claim 1 , wherein:
the determining the third shaded bid value comprises selecting, based upon the plurality of win probabilities associated with the plurality of shaded bid values, the third shaded bid value from the plurality of shaded bid values.
8. The method of claim 3 , wherein:
the determining the third shaded bid value is performed based upon a set of weights, of the set of feature parameters, associated with the second set of features; and
the set of weights comprises the first weight.
9. The method of claim 6 , wherein:
the determining the third shaded bid value is performed based upon:
a set of weights, of the set of feature parameters, associated with the second set of features;
the first bid weight; and
the first bias weight; and
the set of weights comprises the first weight.
10. The method of claim 1 , wherein:
the second auction is a first-price auction.
11. The method of claim 1 , wherein:
the first auction module is the same as the second auction module.
12. The method of claim 1 , wherein:
the first set of features comprises at least one of:
a first internet resource associated with the first request for content;
a first time of day associated with the first request for content;
a first day of week associated with the first request for content; or
a first location associated with the first client device; and
the second set of features comprises at least one of:
a second internet resource associated with the second request for content;
a second time of day associated with the second request for content;
a second day of week associated with the second request for content; or
a second location associated with the second client device.
13. A computing device comprising:
a processor; and
memory comprising processor-executable instructions that when executed by the processor cause performance of operations, the operations comprising:
receiving, by a demand-side platform (DSP), a first bid request, wherein:
the first bid request is associated with a first request for content associated with a first client device; and
the first request for content is indicative of a first set of features comprising one or more first features associated with the first request for content;
determining, based upon a first bid value associated with a first content item, a first shaded bid value associated with the first content item;
submitting, by the DSP, the first shaded bid value to a first auction module, of a supply-side platform (SSP), for participation in a first auction associated with the first request for content;
receiving, by the DSP, a first impression indication indicative of whether the first content item is a winner of the first auction;
storing, in an auction information database, a first set of auction information associated with the first auction, wherein:
the first set of auction information is indicative of:
the first set of features;
the first impression indication; and
the first shaded bid value; and
the auction information database comprises a plurality of sets of auction information, comprising the first set of auction information, associated with a plurality of auctions comprising the first auction;
training a machine learning model using the plurality of sets of auction information to generate a first machine learning model comprising a plurality of feature parameters associated with a plurality of features of the plurality of sets of auction information;
loading the machine learning model onto a bid shading module of the DSP;
receiving, by the DSP, a second bid request, wherein:
the second bid request is associated with a second request for content associated with a second client device; and
the second bid request is indicative of a second set of features comprising one or more second features associated with the second request for content;
determining a second bid value associated with a second content item;
inputting, into the bid shading module of the DSP, the second bid value;
determining, based upon the second set of features and using the first machine learning model loaded onto the bid shading module of the DSP, a plurality of expected bid surpluses associated with a plurality of shaded bid values, wherein:
each shaded bid value of the plurality of shaded bid values does not exceed the second bid value; and
a first expected bid surplus of the plurality of expected bid surpluses is associated with a second shaded bid value of the plurality of shaded bid values;
determining, based upon the plurality of expected bid surpluses and the plurality of shaded bid values, a third shaded bid value; and
submitting the third shaded bid value to a second auction module for participation in a second auction associated with the second request for content,
wherein one or more content items are provided for presentation on the second client device associated with the second request for content based upon a determination that the one or more content items are a winner of the second auction.
14. The computing device of claim 13 , wherein:
the determining the plurality of expected bid surpluses is performed based upon a set of feature parameters, of the plurality of feature parameters, associated with the second set of features.
15. The computing device of claim 14 , wherein:
the first machine learning model comprises a first bias parameter and a first bid parameter; and
the determining the plurality of expected bid surpluses is performed based upon the first bias parameter and the first bid parameter.
16. The computing device of claim 13 , wherein:
the determining the third shaded bid value comprises selecting, based upon the plurality of expected bid surpluses associated with the plurality of shaded bid values, the third shaded bid value from the plurality of shaded bid values.
17. The computing device of claim 16 , wherein:
the selecting the third shaded bid value from the plurality of shaded bid values is performed based upon a determination that the third shaded bid value is associated with a maximum expected bid surplus of the plurality of expected bid surpluses.
18. The computing device of claim 13 , wherein:
the second auction is a first-price auction.
19. The computing device of claim 13 , wherein:
the first set of features comprises at least one of:
a first internet resource associated with the first request for content;
a first time of day associated with the first request for content;
a first day of week associated with the first request for content; or
a first location associated with the first client device; and
the second set of features comprises at least one of:
a second internet resource associated with the second request for content;
a second time of day associated with the second request for content;
a second day of week associated with the second request for content; or
a second location associated with the second client device.
20. A non-transitory machine readable medium having stored thereon processor-executable instructions that when executed cause performance of operations, the operations comprising:
receiving, by a demand-side platform (DSP), a first bid request, wherein:
the first bid request is associated with a first request for content associated with a first client device; and
the first request for content is indicative of a first set of features comprising one or more first features associated with the first request for content;
determining, based upon a first bid value associated with a first content item, a first shaded bid value associated with the first content item;
submitting, by the DSP, the first shaded bid value to a first auction module, of a supply-side platform (SSP), for participation in a first auction associated with the first request for content;
receiving, by the DSP, a first impression indication indicative of whether the first content item is a winner of the first auction;
storing, in an auction information database, a first set of auction information associated with the first auction, wherein:
the first set of auction information is indicative of:
the first set of features;
the first impression indication; and
the first shaded bid value; and
the auction information database comprises a plurality of sets of auction information, comprising the first set of auction information, associated with a plurality of auctions comprising the first auction;
generating, based upon the plurality of sets of auction information, a plurality of feature parameters associated with a plurality of features of the plurality of sets of auction information;
receiving, by the DSP, a second bid request, wherein:
the second bid request is associated with a second request for content associated with a second client device; and
the second bid request is indicative of a second set of features comprising one or more second features associated with the second request for content;
determining a second bid value associated with a second content item;
inputting, into a bid shading module of the DSP, the second bid value;
identifying one or more first feature parameters, of the plurality of feature parameters, associated with the second set of features;
determining, using the bid shading module of the DSP and based upon the one or more first feature parameters, a plurality of expected bid surpluses associated with a plurality of shaded bid values, wherein:
each shaded bid value of the plurality of shaded bid values does not exceed the second bid value; and
a first expected bid surplus of the plurality of expected bid surpluses is associated with a second shaded bid value of the plurality of shaded bid values;
determining, based upon the plurality of expected bid surpluses and the plurality of shaded bid values, a third shaded bid value; and
submitting the third shaded bid value to a second auction module for participation in a second auction associated with the second request for content,
wherein one or more content items are provided for presentation on the second client device associated with the second request for content based upon a determination that the one or more content items are a winner of the second auction.