Automatic performance-triggered campaign adjustment
Automatic performance triggered campaign adjustment. A hierarchical feature tree is generated. Each child node's feature is more specific than its respective parent node's feature. The discovery system creates a behavioral model comprising features of the feature tree which is used in the operation of an advertising campaign. A degraded model feature is detected at the discovery system by comparing a performance metric of a model feature from two different time windows. The discovery system matches a node of the feature tree with the degraded feature and selects a prospective model feature from an ancestor node of the matching feature's node. An estimated performance metric for the prospective model feature is determined and the results are used to decide if the prospective model feature should be incorporated into an updated model or not. The model can be updated with a new model feature selected from one or more prospective model features.
1. A computer-implemented method comprising:
generating a feature tree comprising a root node and a plurality of hierarchically arranged nodes, each node corresponding to a feature of browser histories, each child node corresponding to a feature of increased specificity over a respective parent node's feature;
creating a model, the model configured to assess a browser's suitability for receiving advertising content of an advertising campaign based on features of the browser's history, the model comprising a plurality of features represented in the feature tree;
operating the advertising campaign using the model, the operating comprising;
selecting a plurality of browsers suitable for the advertising campaign according to a result of applying the model to the respective browser's history; and
sending advertising content of the advertising campaign to the plurality of browsers;
responsive to a trigger, initiating detection of a degraded feature, the detection comprising:
comparing a performance metric of a feature of the model from a first time window to a performance metric of the feature of the model from a second time window that is more recent than the first time window, the performance metric of the feature indicating the predictive value of the feature for the success of the advertising campaign;
responsive to a decrease in the performance metric of the feature of the model from the first time window to the second time window, identifying the feature of the model as a degraded feature; and
identifying a feature of the feature tree corresponding to the degraded feature;
automatically updating the model, comprising:
discovering nodes which are ancestor nodes, parent nodes, uncle nodes, grandparent nodes, grand-uncle nodes, great-grandparent nodes, and great-grand-uncle nodes to the degraded feature's corresponding node; and
adding a selected discovered feature corresponding to a node selected from the discovered nodes to the model; and
operating an updated advertising campaign, the operating comprising:
responsive to receiving a notification, from a real-time advertising exchange, of an opportunity to send advertising content to an available browser, applying the updated model to the available browser's history; and
sending advertising content of the advertising campaign to the available browser according to a result of applying the updated model, before the opportunity expires.
2. The method of claim 1 , wherein operating the advertising campaign further comprises monitoring a campaign performance metric of the advertising campaign, and wherein the trigger is a change in the campaign performance metric.
3. The method of claim 2 , wherein the campaign performance metric is based on at least one of a calculated average cost per acquisition (CPA), a conversion rate, and conversion volume.
4. The method of claim 1 , wherein the trigger is a scheduled event.
5. The method of claim 1 , wherein updating the model further comprises deleting the degraded feature from the model.
6. The method of claim 1 , wherein discovering nodes further comprises discovering nodes which are sibling nodes and cousin nodes to the degraded feature's corresponding node.
7. The method of claim 1 , wherein adding the selected discovered feature further comprises:
creating a prospective model comprising the plurality of features represented in the feature tree and comprising the selected discovered feature;
estimating a performance metric of the selected discovered feature of the prospective model by simulating campaign operation with the prospective model; and
based on the estimated performance metric of the selected discovered feature of the prospective model meeting a performance criteria, adding the selected discovered feature.
8. A non-transitory computer-readable storage medium storing processor-executable computer program instructions that, when executed, cause a computer processor to perform a method, the method comprising:
generating a feature tree comprising a root node and a plurality of hierarchically arranged nodes, each node corresponding to a feature of browser histories, each child node corresponding to a feature of increased specificity over a respective parent node's feature;
creating a model, the model configured to assess a browser's suitability for receiving advertising content of an advertising campaign based on features of the browser's history, the model comprising a plurality of features represented in the feature tree;
operating the advertising campaign using the model, the operating comprising;
selecting a plurality of browsers suitable for the advertising campaign according to a result of applying the model to the respective browser's history; and
sending advertising content of the advertising campaign to the plurality of browsers;
responsive to a trigger, initiating detection of a degraded feature, the detection comprising:
comparing a performance metric of a feature of the model from a first time window to a performance metric of the feature of the model from a second time window that is more recent than the first time window, the performance metric of the feature indicating the predictive value of the feature for the success of the advertising campaign;
responsive to a decrease in the performance metric of the feature of the model from the first time window to the second time window, identifying the feature of the model as a degraded feature; and
identifying a feature of the feature tree corresponding to the degraded feature;
automatically updating the model, comprising:
discovering nodes which are ancestor nodes, parent nodes, uncle nodes, grandparent nodes, grand-uncle nodes, great-grandparent nodes, and great-grand-uncle nodes to the degraded feature's corresponding node; and
adding a selected discovered feature corresponding to a node selected from the discovered nodes to the model; and
operating an updated advertising campaign, the operating comprising:
responsive to receiving a notification, from a real-time advertising exchange, of an opportunity to send advertising content to an available browser, applying the updated model to the available browser's history; and
sending advertising content of the advertising campaign to the available browser according to a result of applying the updated model, before the opportunity expires.
9. The medium of claim 8 , wherein operating the advertising campaign further comprises monitoring a campaign performance metric of the advertising campaign, and wherein the trigger is a change in the campaign performance metric.
10. The medium of claim 9 , wherein the campaign performance metric is based on at least one of a calculated average cost per acquisition (CPA), a conversion rate, and conversion volume.
11. The medium of claim 8 , wherein the trigger is a scheduled event.
12. The medium of claim 8 , wherein updating the model further comprises deleting the degraded feature from the model.
13. The medium of claim 8 , wherein discovering nodes further comprises discovering nodes which are sibling nodes and cousin nodes to the degraded feature's corresponding node.
14. The medium of claim 8 , wherein adding the selected discovered feature further comprises:
creating a prospective model comprising the plurality of features represented in the feature tree and comprising the selected discovered feature;
estimating a performance metric of the selected discovered feature of the prospective model by simulating campaign operation with the prospective model; and
based on the estimated performance metric of the selected discovered feature of the prospective model meeting a performance criteria, adding the selected discovered feature.
15. A system comprising:
a processor; and
a non-transitory computer-readable storage medium storing processor-executable computer program instructions that, when executed, cause a computer processor to perform a method, the method comprising:
generating a feature tree comprising a root node and a plurality of hierarchically arranged nodes, each node corresponding to a feature of browser histories, each child node corresponding to a feature of increased specificity over a respective parent node's feature;
creating a model, the model configured to assess a browser's suitability for receiving advertising content of an advertising campaign based on features of the browser's history, the model comprising a plurality of features represented in the feature tree;
operating the advertising campaign using the model, the operating comprising;
selecting a plurality of browsers suitable for the advertising campaign according to a result of applying the model to the respective browser's history; and
sending advertising content of the advertising campaign to the plurality of browsers;
responsive to a trigger, initiating detection of a degraded feature, the detection comprising:
comparing a performance metric of a feature of the model from a first time window to a performance metric of the feature of the model from a second time window that is more recent than the first time window, the performance metric of the feature indicating the predictive value of the feature for the success of the advertising campaign;
responsive to a decrease in the performance metric of the feature of the model from the first time window to the second time window, identifying the feature of the model as a degraded feature; and
identifying a feature of the feature tree corresponding to the degraded feature; automatically updating the model, comprising:
discovering nodes which are ancestor nodes, parent nodes, uncle nodes, grandparent nodes, grand-uncle nodes, great-grandparent nodes, and great-grand-uncle nodes to the degraded feature's corresponding node; and
adding a selected discovered feature corresponding to a node selected from the discovered nodes to the model; and
operating an updated advertising campaign, the operating comprising:
responsive to receiving a notification, from a real-time advertising exchange, of an opportunity to send advertising content to an available browser, applying the updated model to the available browser's history; and
sending advertising content of the advertising campaign to the available browser according to a result of applying the updated model, before the opportunity expires.
16. The system of claim 15 , wherein operating the advertising campaign further comprises monitoring a campaign performance metric of the advertising campaign, and wherein the trigger is a change in the campaign performance metric.
17. The system of claim 16 , wherein the campaign performance metric is based on at least one of a calculated average cost per acquisition (CPA), a conversion rate, and conversion volume.
18. The system of claim 15 , wherein the trigger is a scheduled event.
19. The system of claim 15 , wherein updating the model further comprises deleting the degraded feature from the model.
20. The system of claim 15 , wherein discovering nodes further comprises discovering nodes which are sibling nodes and cousin nodes to the degraded feature's corresponding node.
21. The system of claim 15 , wherein adding the selected discovered feature further comprises:
creating a prospective model comprising the plurality of features represented in the feature tree and comprising the selected discovered feature;
estimating a performance metric of the selected discovered feature of the prospective model by simulating campaign operation with the prospective model; and
based on the estimated performance metric of the selected discovered feature of the prospective model meeting a performance criteria, adding the selected discovered feature.