Content item placement optimization system
Disclosed herein are system, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for optimizing content item placements on a content publisher application of a media device based on multi-publisher content item measurement data associated with a set of media devices. An example embodiment operates by receiving multi-publisher content item measurement data that comprises data signals for a plurality of content items from a plurality of different publishers that are presented at a plurality of different households. A content item, from among the plurality of content items, is determined to be transmitted to a media device of a particular household for presentation via a content publisher application of the media device. In response to determining that the content item is to be transmitted to the media device, the content item is transmitted to the media device for presentation via the content publisher application of the media device.
1 . A computer-implemented method, comprising:
receiving, by at least one computer processor, multi-publisher content item measurement data that comprises data signals for a plurality of content items from a plurality of different publishers that are presented at a plurality of different households;
determining, based on the multi-publisher content item measurement data, a content item from among the plurality of content items is to be transmitted to a media device of a particular household of the plurality of different households for presentation via a content publisher application of the media device; and
in response to determining that the content item is to be transmitted to the media device, transmitting the content item to the media device for presentation via the content publisher application of the media device.
2 . The computer-implemented method of claim 1 , wherein receiving the multi-publisher content item measurement data comprises:
receiving, via a data feed, first multi-publisher content item measurement data pertaining to one or more households in the plurality of different households for a first time period; and
receiving, via the data feed, second multi-publisher content item measurement data pertaining to one or more households in the plurality of different households for a second time period.
3 . The computer-implemented method of claim 1 , wherein the data signals comprise at least one of:
information concerning content item impressions with respect to the plurality of content items that occurred via the media device; or
information concerning content item impressions with respect to the plurality of content items that occurred at each of the plurality of different households at which other media devices are located.
4 . The computer-implemented method of claim 3 , wherein the information concerning the content item impressions with respect to the plurality of content items that occurred via the media device comprises a value that indicates that the content item impressions occurred via one of:
the content publisher application of the media device;
a third-party content publisher application of the media device; or
linear programming viewed via the media device.
5 . The computer-implemented method of claim 3 , wherein the data signals comprise at least one of:
information concerning user conversions with respect to the plurality of content items that was attributed to the particular household at which the media device is located; or
information concerning user conversions with respect to the plurality of content items that was attributed to each of the plurality of different households at which other media devices are located.
6 . The computer-implemented method of claim 1 , wherein determining the content item is to be transmitted to the media device comprises:
determining, based at least on the multi-publisher content item measurement data, that presenting the content item via the content publisher application of the media device will increase an incremental reach of a campaign associated with the content item.
7 . The computer-implemented method of claim 1 , wherein determining the content item is to be transmitted to the media device comprises:
determining, based at least on the multi-publisher content item measurement data, that presenting the content item via the content publisher application of the media device will increase a probability of a user conversion.
8 . The computer-implemented method of claim 1 , wherein determining the content item is to be transmitted to the media device comprises:
providing, as an input, an identifier of a content item of the plurality of content items to a machine learning model;
obtaining, from the machine learning model, a confidence level for the content item indicating at least one of a likelihood that presenting the content item via the content publisher application of the media device will increase an incremental reach of a campaign associated with the content item or a likelihood that presenting the content item via the content publisher application of the media device will increase a probability of a user conversion; and
determining that the content item is to be transmitted to the media device based on the confidence level meeting a predetermined threshold, wherein the machine learning model is trained based at least on the multi-publisher content item measurement data.
9 . A system, comprising:
one or more memories; and
at least one processor each coupled to at least one of the one or more memories and configured to perform operations comprising:
receiving multi-publisher content item measurement data that comprises data signals for a plurality of content items from a plurality of different publishers that are presented at a plurality of different households;
determining, based on the multi-publisher content item measurement data, a content item from among the plurality of content items is to be transmitted to a media device of a particular household of the plurality of different households for presentation via a content publisher application of the media device; and
in response to determining that the content item is to be transmitted to the media device, transmitting the content item to the media device for presentation via the content publisher application of the media device.
10 . The system of claim 9 , wherein receiving the multi-publisher content item measurement data comprises:
receiving, via a data feed, first multi-publisher content item measurement data pertaining to one or more households in the plurality of different households for a first time period; and
receiving, via the data feed, second multi-publisher content item measurement data pertaining to one or more households in the plurality of different households for a second time period.
11 . The system of claim 9 , wherein the data signals comprise at least one of:
information concerning content item impressions with respect to the plurality of content items that occurred via the media device; or
information concerning content item impressions with respect to the plurality of content items that occurred at each of the plurality of different households at which other media devices are located.
12 . The system of claim 11 , wherein the information concerning the content item impressions with respect to the plurality of content items that occurred via the media device comprises a value that indicates that the content item impressions occurred via one of:
the content publisher application of the media device;
a third-party content publisher application of the media device; or
linear programming viewed via the media device.
13 . The system of claim 11 , wherein the data signals comprise at least one of:
information concerning user conversions with respect to the plurality of content items that was attributed to the particular household at which the media device is located; or
information concerning user conversions with respect to the plurality of content items that was attributed to each of the plurality of different households at which other media devices are located.
14 . The system of claim 9 , wherein determining the content item is to be transmitted to the media device comprises:
determining, based at least on the multi-publisher content item measurement data, that presenting the content item via the content publisher application of the media device will increase an incremental reach of a campaign associated with the content item.
15 . The system of claim 9 , wherein determining the content item is to be transmitted to the media device comprises:
determining, based at least on the multi-publisher content item measurement data, that presenting the content item via the content publisher application of the media device will increase a probability of a user conversion.
16 . The system of claim 9 , wherein determining the content item is to be transmitted to the media device comprises:
providing, as an input, an identifier of a content item of the plurality of content items to a machine learning model;
obtaining, from the machine learning model, a confidence level for the content item indicating at least one of a likelihood that presenting the content item via the content publisher application of the media device will increase an incremental reach of a campaign associated with the content item or a likelihood that presenting the content item via the content publisher application of the media device will increase a probability of a user conversion; and
determining that the content item is to be transmitted to the media device based on the confidence level meeting a predetermined threshold, wherein the machine learning model is trained based at least on the multi-publisher content item measurement data.
17 . A non-transitory computer-readable medium having instructions stored thereon that, when executed by at least one computing device, cause the at least one computing device to perform operations comprising:
receiving multi-publisher content item measurement data that comprises data signals for a plurality of content items from a plurality of different publishers that are presented at a plurality of different households;
determining, based on the multi-publisher content item measurement data, a content item from among the plurality of content items is to be transmitted to a media device of a particular household of the plurality of different households for presentation via a content publisher application of the media device; and
in response to determining that the content item is to be transmitted to the media device, transmitting the content item to the media device for presentation via the content publisher application of the media device.
18 . The non-transitory computer-readable medium of claim 17 , wherein receiving the multi-publisher content item measurement data comprises:
receiving, via a data feed, first multi-publisher content item measurement data pertaining to one or more households in the plurality of different households for a first time period; and
receiving, via the data feed, second multi-publisher content item measurement data pertaining to one or more households in the plurality of different households for a second time period.
19 . The non-transitory computer-readable medium of claim 17 , wherein the data signals comprise at least one of:
information concerning content item impressions with respect to the plurality of content items that occurred via the media device; or
information concerning content item impressions with respect to the plurality of content items that occurred at each of the plurality of different households at which other media devices are located.
20 . The non-transitory computer-readable medium of claim 19 , wherein the information concerning the content item impressions with respect to the plurality of content items that occurred via the media device comprises a value that indicates that the content item impressions occurred via one of:
the content publisher application of the media device;
a third-party content publisher application of the media device; or
linear programming viewed via the media device.