Conversion timing prediction for networked advertising
A computer-implemented method for conversion timing inference. A conversion timing model is model is configured to predict a likelihood of conversion based on an entity's elapsed time since a qualified entry event. The conversion timing model is constructed based on a distribution of the conversion timespans of converters. Each conversion timespan describes a length of time between a qualified entry event and a conversion event for a converted entity. A notification of an opportunity to expose a candidate entity to networked content is received and the likelihood of conversion for the candidate entity is determined by: determining an elapsed time since a qualified entry event for the candidate entity and applying the conversion timing model to the elapsed time. A response to the notification based on the likelihood of conversion for the candidate entity is prepared. Timely responses may include the selection of customized content, customized advertising content or bid values.
1. A computer-implemented method comprising:
receiving, from a data repository, histories of a plurality of converted entities, each history comprising time-stamped records of events associated with a respective entity;
calculating a conversion timespan for each converted entity by:
selecting a time-stamped conversion event from a respective converted entity's history according to conversion event criteria;
selecting a time-stamped entry event occurring before the time-stamped conversion event from the respective converted entity's history according to entry event criteria; and
calculating an elapsed time between the time-stamped entry event and the time-stamped conversion event;
constructing a conversion timing model based on a distribution of the calculated conversion timespans, wherein the conversion timing model is configured to predict a likelihood of conversion for an entity based on the entity's elapsed time since the entity's time-stamped entry event meeting the entry event criteria;
receiving, from a real time bidding exchange, notification of an opportunity to bid on an advertising exposure associated with a candidate entity;
responsive to receiving notification of the opportunity to bid, determining a time stamp of a qualified entry event of the candidate entity, according to the entry event criteria;
identifying the candidate entity's elapsed time since the candidate entity's qualified entry event;
calculating a likelihood of conversion for the candidate entity by applying the conversion timing model to the elapsed time since the candidate entity's qualified entry event; and
preparing a response to the notification based on the likelihood of conversion for the candidate entity.
2. The method of claim 1 wherein:
the notification comprises a bid request.
3. The method of claim 1 wherein:
calculating comprises predicting a likelihood of conversion within a time window; and
preparing comprises preparing a response to the notification based on the likelihood of conversion for the candidate entity within the time window.
4. The method of claim 1 wherein:
constructing comprises fitting the distribution of calculated conversion timespans with a gamma mixture model configured with a number of conversion modes.
5. The method of claim 1 wherein:
preparing a response comprises selecting a bid price.
6. The method of claim 1 wherein:
preparing a response comprises selecting an advertising creative.
7. The method of claim 1 wherein:
preparing comprises selecting customized content.
8. A system comprising:
a processor;
a computer readable storage medium storing processor-executable computer program instructions, the instructions comprising instructions for:
receiving, from a data repository, histories of a plurality of converted entities, each history comprising time-stamped records of events associated with a respective entity;
calculating a conversion timespan for each converted entity by:
selecting a time-stamped conversion event from a respective converted entity's history according to conversion event criteria;
selecting a time-stamped entry event occurring before the time-stamped conversion event from the respective converted entity's history according to entry event criteria; and
calculating an elapsed time between the time-stamped entry event and the time-stamped conversion event;
constructing a conversion timing model based on a distribution of the calculated conversion timespans, wherein the conversion timing model is configured to predict a likelihood of conversion for an entity based on the entity's elapsed time since the entity's time-stamped entry event meeting the entry event criteria;
receiving, from a real time bidding exchange, notification of an opportunity to bid on an advertising exposure associated with a candidate entity;
responsive to receiving notification of the opportunity to bid, determining a time stamp of a qualified entry event of the candidate entity, according to the entry event criteria;
identifying the candidate entity's elapsed time since candidate entity's qualified entry event;
calculating a likelihood of conversion for the candidate entity by applying the conversion timing model to the elapsed time since the candidate entity's qualified entry event; and
preparing a response to the notification based on the likelihood of conversion for the candidate entity.
9. The system of claim 8 wherein:
the notification comprises a bid request.
10. The system of claim 8 wherein:
calculating comprises predicting a likelihood of conversion within a time window; and
preparing comprises preparing a response to the notification based on the likelihood of conversion for the candidate entity within the time window.
11. The system of claim 8 wherein:
constructing comprises fitting the distribution of calculated conversion timespans with a gamma mixture model configured with a number of conversion modes.
12. A non-transitory computer readable storage medium executing computer program instructions, the computer program instructions comprising instructions for:
receiving, from a data repository, histories of a plurality of converted entities, each history comprising time-stamped records of events associated with a respective entity;
calculating a conversion timespan for each converted entity by:
selecting a time-stamped conversion event from a respective converted entity's history according to conversion event criteria;
selecting a time-stamped entry event occurring before the time-stamped conversion event from the respective converted entity's history according to entry event criteria; and
calculating an elapsed time between the time-stamped entry event and the time-stamped conversion event;
constructing a conversion timing model based on a distribution of the calculated, conversion timespans, wherein the conversion timing model is configured to predict a likelihood of conversion for an entity based on the entity's elapsed time since the entity's time-stamped entry event meeting the entry event criteria;
receiving, from a real time bidding exchange, notification of an opportunity to bid on an advertising exposure associated with a candidate entity;
responsive to receiving notification of the opportunity to bid, determining a time stamp of a qualified entry event of the candidate entity, according to the entry event criteria;
identifying the candidate entity's elapsed time since the candidate entity's qualified entry event;
calculating a likelihood of conversion for the candidate entity by applying the conversion timing model to the elapsed time since the candidate entity's qualified entry event; and
preparing a response to the notification based on the likelihood of conversion for the candidate entity.
13. The medium of claim 12 wherein:
calculating comprises predicting a likelihood of conversion within a time window; and
preparing comprises preparing a response to the notification based on the likelihood of conversion for the candidate entity within the time window.
14. The medium of claim 12 wherein:
constructing comprises fitting the distribution of calculated conversion timespans with a gamma mixture model configured with a number of conversion modes.
15. The medium of claim 12 wherein:
the notification comprises a bid request.
16. The method of claim 5 further comprising:
bidding on the opportunity at the selected bid price.
17. The method of claim 6 further comprising:
sending the selected advertising creative to the candidate entity.
18. The method of claim 7 further comprising:
sending the selected customized content to the candidate entity.
19. The system of claim 8 wherein:
preparing a response comprises selecting a bid price; and
the instructions further comprise instructions for:
bidding on the opportunity at the selected bid price.
20. The medium of claim 12 wherein:
preparing a response comprises selecting a bid price; and
the computer program instructions further comprise instructions for:
bidding on the opportunity at the selected bid price.