DETERMINING WHETHER TO PLACE AN ADVERTISEMENT REQUESTING AN ADDRESS
Disclosed herein is a system and method to determine whether to place an advertisement to a user requesting an address from the user. The system can iteratively determine multiple advertisement metrics of multiple advertisements to obtain multiple metrics. An advertisement metric among the multiple advertising metrics can indicate the value of placing the advertisement to the user. The system can rank multiple advertisements based on the multiple advertisement metrics and present a predetermined percentage of top-ranking advertisements among the multiple advertisements.
1 . A computer-implemented method comprising:
accessing content value data for presenting interactive content, the content value data comprising one or more of account profile information, a content time value, and a content value;
generating, utilizing a machine learning model, a content interaction prediction by predicting a series of client device interactions with the interactive content according to the content value data;
generating a combined content value prediction by adjusting the content interaction prediction according to a content fulfillment value prediction corresponding to a value of completing an action associated with the interactive content; and
providing the interactive content for display on a client device based on the combined content value prediction.
2 . The computer-implemented method of claim 1 , wherein accessing content value data comprises determining, for the account profile information, one or more of a content interaction frequency value or an account profile demographic value.
3 . The computer-implemented method of claim 1 , wherein generating the content interaction prediction comprises:
generating one or more content interaction proxy predictions comprising an initial content interaction proxy prediction, a content destination interaction proxy prediction, a content delivery proxy prediction, or a content installation proxy prediction; and
combining the one or more content interaction proxy predictions.
4 . The computer-implemented method of claim 3 , wherein combining the one or more content interaction proxy predictions comprises:
determining, utilizing the machine learning model, correlation values corresponding to the one or more content interaction proxy predictions; and
combining the one or more content interaction proxy predictions according to the correlation values.
5 . The computer-implemented method of claim 1 , wherein generating the combined content value prediction comprises:
generating a default content fulfillment value prediction;
generating the content fulfillment value prediction by adjusting the default content fulfillment value prediction according to the content value data; and
utilizing the content fulfillment value prediction to adjust the content interaction prediction.
6 . The computer-implemented method of claim 1 , further comprising:
generating a plurality of combined content value predictions corresponding to a plurality of interactive content;
generating a ranking of the plurality of combined content value predictions;
selecting an interactive content from the plurality of interactive content according to the ranking of the plurality of combined content value predictions; and
providing the selected interactive content for display on the client device.
7 . The computer-implemented method of claim 1 , further comprising installing an application associated with the interactive content in response to the client device interacting with the interactive content.
8 . A system comprising:
at least one processor; and
at least one non-transitory computer-readable storage medium storing instructions that, when executed by the at least one processor, cause the system to:
generate, utilizing a machine learning model, a content interaction prediction by predicting a series of client device interactions with interactive content according to content value data associated with a client account;
generate a combined content value prediction by adjusting the content interaction prediction according to a content fulfillment value prediction corresponding to a value of completing an action associated with the interactive content; and
provide the interactive content for display on a client device based on the combined content value prediction.
9 . The system of claim 8 , further comprising instructions that, when executed by the at least one processor, cause the system to determine, for the content value data associated with a client account, one or more of a content interaction frequency value or an account profile demographic value.
10 . The system of claim 8 , further comprising instructions that, when executed by the at least one processor, cause the system to generate the content interaction prediction by combining one or more content interaction proxy predictions corresponding to one or more proxy predictions corresponding to interaction with the interactive content.
11 . The system of claim 10 , further comprising instructions that, when executed by the at least one processor, cause the system to combine the one or more content interaction proxy predictions by selectively weighting the one or more content interaction proxy predictions according to correlation values determined by the machine learning model.
12 . The system of claim 8 , further comprising instructions that, when executed by the at least one processor, cause the system to generate the combined content value prediction by:
generating the content fulfillment value prediction by adjusting a default content fulfillment value prediction according to the content value data; and
utilizing the content fulfillment value prediction to adjust the content interaction prediction.
13 . The system of claim 8 , further comprising instructions that, when executed by the at least one processor, cause the system to:
generate a second combined content value prediction corresponding to a second interactive content;
generate a ranking of the combined content value prediction and the second combined content value prediction; and
select the second interactive content for display on the client device in response to determining that the second combined content value prediction exceeds the combined content value prediction.
14 . The system of claim 8 , further comprising installing an application associated with the interactive content in response to a client device interacting with the interactive content.
15 . A non-transitory computer-readable medium storing instructions that, when executed by at least one processor, cause a computer system to:
access content value data for presenting interactive content, the content value data comprising one or more of account profile information, a content time value, and a content value;
generate, utilizing a machine learning model, predictions for a series of client device interactions with the interactive content according to the content value data;
generate, utilizing the machine learning model, a content interaction prediction by combining the predictions for a series of client device interactions;
generate a combined content value prediction by adjusting the content interaction prediction according to a content fulfillment value prediction corresponding to a value of completing an action associated with the interactive content; and
provide the interactive content for display on a client device based on the combined content value prediction.
16 . The non-transitory computer-readable medium of claim 15 , further comprising instructions that, when executed by the at least one processor, cause the computer system to access content value data by:
accessing a client account associated with the account profile information; and
determining, for the client account, one or more of a content interaction frequency value or an account profile demographic value.
17 . The non-transitory computer-readable medium of claim 15 , further comprising instructions that, when executed by the at least one processor, cause the computer system to generate predictions for a series of client device interactions by:
determining one or more client device interaction proxies; and
generating one or more content interaction proxy predictions corresponding to the one or more client device interaction proxies.
18 . The non-transitory computer-readable medium of claim 15 , further comprising instructions that, when executed by the at least one processor, cause the computer system to generate the combined content value prediction by:
generating the content fulfillment value prediction by adjusting a default content fulfillment value prediction according to the content value data; and
utilizing the content fulfillment value prediction to adjust the content interaction prediction.
19 . The non-transitory computer-readable medium of claim 15 , further comprising instructions that, when executed by the at least one processor, cause the computer system to:
generate a plurality of combined content value predictions corresponding to a plurality of interactive content;
determine a subset of combined content value predictions corresponding to a subset of interactive content by comparing the plurality of combined content value predictions to an interactive content value threshold;
generating a ranking of the subset of combined content value predictions;
selecting an interactive content from the subset of interactive content according to the ranking of the subset of combined content value predictions; and
providing the selected interactive content for display on the client device.
20 . The non-transitory computer-readable medium of claim 15 , further comprising instructions that, when executed by the at least one processor, cause the computer system to install an application associated with the interactive content in response to the client device interacting with the interactive content.