Advertising model
Tiered advertisement bidding is disclosed. One or more quality metrics associated with a user profile are determined. An advertisement bid is selected from a plurality of tiered bids based at least in part on the determined quality metrics. Determining the quality metrics can include determining a conversion assessment. Determining the quality metric can also include determining whether a need associated with a user profile has been met for a category. In some cases, persona detection is performed with respect to the user profile.
1 . An advertisement platform, comprising:
a network interface;
a memory, storing instructions; and
a processor configured to communicate data with the network interface, and the memory, the processor further configured to execute the instructions to:
determine a first indication of interest in a first category, wherein:
the first indication of interest corresponds to a user profile, accessed using the network interface, that is associated with the advertisement platform;
the user profile has performed, through the network interface:
an attempt to access a previous resource; and
a plurality of online purchases;
the first indication of interest is based, at least in part, on at least one of:
a first search performed through the user profile; or
a first purchase of the plurality of online purchases; and
determining the first indication of interest comprises;
storing, in a record associated with the user profile, the first indication of interest in the first category; and
accessing an identifier, associated with the user profile, that is derived using at least one of an HTML cookie, a cache cookie, or a user agent;
receive, through the network interface, a confirmation that a need for a current resource is met for the user profile, wherein:
the current resource belongs to the first category; and
the need being met occurs following a second purchase of the plurality of online purchases; and
when the need for the current resource is met:
determining a second indication of interest, belonging to a second category, wherein the first category and the second category are topically related; and
initiating a projection of an advertisement for the user profile on a display associated with the user profile, wherein the advertisement based, at least in part, on the second indication of interest.
2 . The advertisement platform of claim 1 , wherein accessing the identifier comprises at least one of retrieving the identifier from storage, retrieving the identifier using the network interface, or computing the identifier based on a counter.
3 . The advertisement platform of claim 1 , wherein the record is stored in a data repository incorporated into the advertisement platform and anonymized, at least in part.
4 . The advertisement platform of claim 1 , wherein:
the second indication of interest is derived from an assessment of a purchase likelihood associated with the user profile; and
the purchase likelihood is a conditional likelihood determined used to select the advertisement.
5 . The advertisement platform of claim 1 , wherein at least one of a discount or a surcharge is:
associated with the advertisement; and
determined from the second indication of interest.
6 . The advertisement platform of claim 1 , wherein at least one of the first indication of interest or the second indication of interest is derived using a machine learning algorithm.
7 . A method for implementing advertisements, the method comprising:
determining, with a processor, a first indication of interest in a first category, wherein:
the first indication of interest corresponds to a user profile associated with a device;
the user profile has performed:
an attempt to access a previous resource using the device; and
a plurality of online purchases;
the first indication of interest is based, at least in part, on at least one of:
a first search performed through the user profile; or
a first purchase of the plurality of online purchases; and
determining the first indication of interest comprises;
storing, in a record associated with the user profile, the first indication of interest in the first category; and
accessing an identifier, associated with the user profile, that is derived using at least one of an HTML cookie, a cache cookie, or a user agent,
receiving a confirmation that a need for a current resource is met for the user profile, wherein:
the current resource belongs to the first category; and
the need being met occurs following a second purchase of the plurality of online purchases; and
when the need for the current resource is met:
determining, using the processor, a second indication of interest, belonging to a second category, wherein the first category and the second category are topically related; and
initiating a projection of an advertisement for the user profile on a display associated with the user profile, wherein the advertisement based, at least in part, on the second indication of interest.
8 . The method of claim 7 , wherein accessing the identifier comprises at least one of retrieving the identifier from storage, retrieving the identifier using a network interface, or computing the identifier based on a counter.
9 . The method of claim 7 , wherein the record is stored in a data repository and anonymized, at least in part.
10 . The method of claim 7 , wherein:
the second indication of interest is derived from an assessment of a purchase likelihood associated with the user profile; and
the purchase likelihood is a conditional likelihood determined used to select the advertisement.
11 . The method of claim 7 , wherein at least one of a discount or a surcharge is:
associated with the advertisement; and
determined from the second indication of interest.
12 . The method of claim 7 , wherein at least one of the first indication of interest or the second indication of interest is derived using a machine learning algorithm.
13 . A non-transitory computer-readable medium comprising instructions that, when executed, are configured to cause a processor to perform a process for advertisement, the process comprising:
determining a first indication of interest in a first category, wherein:
the first indication of interest corresponds to a user profile associated with a device;
the user profile has performed:
an attempt to access a previous resource using the device; and
a plurality of online purchases;
the first indication of interest is based, at least in part, on at least one of:
a first search performed through the user profile; or
a first purchase of the plurality of online purchases; and
determining the first indication of interest comprises;
storing, in a record associated with the user profile, the first indication of interest in the first category; and
accessing an identifier, associated with the user profile, that is derived using at least one of an HTML cookie, a cache cookie, or a user agent,
receiving a confirmation that a need for a current resource is met for the user profile, wherein:
the current resource belongs to the first category; and
the need being met occurs following a second purchase of the plurality of online purchases; and
when the need for the current resource is met:
determining a second indication of interest, belonging to a second category, wherein the first category and the second category are topically related; and
initiating a projection of an advertisement for the user profile on a display associated with the user profile, wherein the advertisement based, at least in part, on the second indication of interest.
14 . The non-transitory computer-readable medium of claim 13 , wherein accessing the identifier comprises at least one of retrieving the identifier from storage, retrieving the identifier using a network interface, or computing the identifier based on a counter.
15 . The non-transitory computer-readable medium of claim 13 , wherein the record is stored in a data repository and anonymized, at least in part.
16 . The non-transitory computer-readable medium of claim 13 , wherein:
the second indication of interest is derived from an assessment of a purchase likelihood associated with the user profile; and
the purchase likelihood is a conditional likelihood determined used to select the advertisement.
17 . The non-transitory computer-readable medium of claim 13 , wherein at least one of a discount or a surcharge is:
associated with the advertisement; and
determined from the second indication of interest.
18 . The non-transitory computer-readable medium of claim 13 , wherein at least one of the first indication of interest or the second indication of interest is derived using a machine learning algorithm.