Systems and methods for automatically generating remarketing lists
Systems and methods for automatically generating remarketing lists based on client sessions are provided. The system can include a visitor management module to identify client sessions established at a website. The visitor management module can determine node pairs including destination nodes and referrer nodes. The system can include a graph construction module to construct a graph including the node pairs and edges between the node pairs representing click-through rates. The system can include a graph clustering module to assign information resources to a first group based on one of i) a number of edges between the nodes and a conversion node or ii) click-through rates of node pairs including. The system includes a remarketing list generation module to assign the first group of information resources to a remarketing list. The remarketing list generation module can assign client identifiers that accessed the first group of information resources to the remarketing list.
1. A system for automatically generating remarketing lists based on sessions, comprising: one or more processors and a memory, the one or more processors configured to: receive reporting data associated with client device visits to information resources, the reporting data being generated via execution of online reporting scripts embedded in the information resources;
identify, based on the received reporting data, one or more client sessions, each client session of the one or more client sessions corresponding to a client device visiting one or more information resources;
determine, from each client session of the one or more client sessions and based on the received reporting data, a plurality of information resource pairs, each information resource pair of the plurality of information resource pairs including a destination information resource and a referrer information resource from which the client device visited the destination information resource;
construct, using the one or more client sessions, a graph including the plurality of information resource pairs and a respective plurality of edges between the destination information resources and corresponding referrer information resources of the plurality of information resource pairs, wherein each edge of the plurality of edges represents an interaction metric based on a number of client devices that visited the destination information resource of the respective information resource pair from the corresponding referrer information resource of the respective information resource pair, and wherein at least one pair of the plurality of information resource pairs includes a conversion information resource;
implement a graph clustering module to select, from the plurality of information resource pairs and based on (i) the interaction metrics represented by the corresponding edges and (ii) a number of edges between at least some information resources in the plurality of information resource pairs and the conversion information resource, a subset of information resource pairs, wherein the interaction metrics include weights of click-through rates between the referrer information resource and the destination information resource of the plurality of information resource pairs; and
generate a client identifier list including one or more client device identifiers each associated with a respective client session of the one or more client sessions that visited a corresponding referrer information resource of at least one information resource pair of the subset of information resource pairs.
2. The system of claim 1 , wherein the one or more processors are further configured to maintain, in one or more data structures, an association between a content item and the client identifier list in response to a request from a content provider of the content item.
3. The system of claim 1 , wherein the one or more processors are further configured to receive one or more of an identity of a destination information resource, an identity of a referrer information resource, or times at which the destination information resource and the referrer information resource were visited by a client device.
4. The system of claim 1 , wherein the one or more processors are further configured to restrict, from selection in the subset of information resource pairs, at least one information resource pair that is associated with a corresponding interaction metric that is less than a threshold.
5. The system of claim 1 , wherein the one or more processors are further configured to identify a number of information resource pairs that include the same destination information resource and different referrer information resources.
6. The system of claim 5 , wherein the one or more processors are further configured to identify the subset of information resource pairs based on a number of the plurality of information resource pairs including the same destination information resource and different referrer information resource pairs exceeding a threshold.
7. The system of claim 6 , wherein the one or more processors, in identifying the subset of information resource pairs, are further configured to:
determine a click-through rate threshold; and
identify one or more information resource pairs including the same referrer node and a click-through rate greater than the click-through rate threshold as a part of the subset of information resource pairs.
8. A method for automatically generating remarketing lists based on sessions, comprising:
receiving, by a data processing system comprising one or more processors and a memory, reporting data associated with client device visits to information resources, the reporting data being generated via execution of online reporting scripts embedded in the information resources;
identifying, by the data processing system and based on the received reporting data, each client session of the one or more client sessions corresponding to a client device visiting one or more information resources;
determining, by the data processing system, from each client session of the one or more client sessions and based on the received reporting data, a plurality of information resource pairs, each information resource pair of the plurality of information resource pairs including a destination information resource and a referrer information resource from which the client device visited the destination information resource;
constructing, by the data processing system and using the one or more client sessions, a graph including the plurality of information resource pairs and a respective plurality of edges between the destination information resources and corresponding referrer information resources of the plurality of information resource pairs, wherein each edge of the plurality of edges represents an interaction metric based on a number of client devices that visited the destination respective information resource of the information resource pair from the corresponding referrer information resource of the respective information resource pair, and wherein at least one pair of the plurality of information resource pairs includes a conversion information resource;
implementing, by the data processing system, a graph clustering module to select, from the plurality of information resource pairs and based on (i) the interaction metrics represented by the corresponding edges and (ii) a number of edges between at least some information resources in the plurality of information resource pairs and the conversion information resource, a subset of information resource pairs, wherein the interaction metrics include weights of click-through rates between the referrer information resource and the destination information resource of the plurality of information resource pairs; and
generating, by the data processing system, a client identifier list including client device identifiers each associated with a respective client session of the one or more client sessions that visited a corresponding referrer information resource of at least one information resource pair of the subset of information resource pairs.
9. The method of claim 8 , further comprising maintaining, by the data processing system, in one or more data structures, an association between a content item and the client identifier list in response to a request from a content provider of the content item.
10. The method of claim 8 , further comprising receiving, by the data processing system, one or more of an identity of a destination information resource, an identity of a referrer information resource, or times at which the destination information resource and the referrer information resource were visited by a client device.
11. The method of claim 8 , further comprising restricting, by the data processing system, from selection in the subset of information resource pairs, at least one information resource pair that is associated with a corresponding interaction metric that is less than a threshold.
12. The method of claim 8 , further comprising identifying, by the data processing system, a number of information resource pairs that include the same destination information resource and different referrer information resources.
13. The method of claim 12 , wherein identifying the subset of information resource pairs is based on a number of the plurality of information resource pairs including the same destination information resource and different referrer information resource pairs exceeding a threshold.
14. The method of claim 13 , wherein identifying the subset of information resource pairs further comprises:
determining, by the data processing system, a click-through rate threshold; and
identifying, by the data processing system, one or more information resource pairs including the same referrer node and a click-through rate greater than the click-through rate threshold as a part of the subset of information resource pairs.