Generated messaging to view content on media devices
Techniques, systems, and methods are disclosed to generate messaging to view content on media devices based on predictive factors. Information may be received to trigger one or more predictive factors and then generate a candidate set of offers to view content at a media device based on the information. Based on the one or more predictive factors, confidence values may be determined for each offer in the candidate set of offers. The candidate set of offers may be ranked based on the associated confidence values. Subsequently, presentation of at least one offer of the candidate set of offers may be caused to display in a user interface screen on the media device based on the ranking.
1. A method comprising:
determining that a content item was partially viewed;
in response to determining that the content item was partially viewed, boosting a predictive factor associated with the content item;
in response to determining that the content item is an episode of a series, wherein a number of episodes of the series were previously viewed, further boosting the predictive factor associated with the content item;
decaying, after the boosting, the predictive factor at a decay rate over a time period, wherein the time period begins when the partially viewed content item was partially viewed, wherein the decay rate is correlated with the boosting by determining the decay rate based on a same cause for the boosting; and
causing, via a user interface, a display of an offer to view the partially viewed content item, based on the predictive factor.
2. The method of claim 1 , wherein the predictive factor is triggered by at least one of (a) a day and time combination associated with a user behavior associated with a particular content item, and (b) partially viewed duration time value associated with a particular content item.
3. The method of claim 1 , further comprising:
generating a candidate set of offers by determining the candidate set of offers to view one or more recorded content items available on a media device based, at least in part, on one or more predictive factors associated with the content including at least one or more of linear content, partially viewed content, over-the-top content, recorded asset content, content associated with a collection affinity value, or content associated with a genre affinity value; and
selecting the candidate set of offers based on a variety of metrics associated with each offer of the candidate set of offers.
4. The method of claim 3 , wherein generating the candidate set of offers to view content further comprises:
determining a frequency of consumption rate based on user watching behavior associated with the series; and
based on the frequency of consumption rate, determining the candidate set of offers associated with the content including at least one or more of over-the-top content or recorded asset content, the content further comprising a next episode in the series.
5. The method of claim 3 , further comprising:
receiving a user input associated with a presentation of at least one candidate offer via the user interface;
updating one or more confidence values associated with the one or more predictive factors associated with the at least one candidate offer based on the user input.
6. A system comprising:
control circuitry configured to:
determine that a content item was partially viewed;
in response to determining that the content item was partially viewed, boost a predictive factor associated with the content item;
in response to determining that the content item is an episode of a series, wherein a number of episodes of the series were previously viewed, further boost the predictive factor associated with the content item;
decay, after the boosting, the predictive factor at a decay rate over a time period, wherein the time period begins when the partially viewed content item was partially viewed, wherein the decay rate is correlated with the boosting by determining the decay rate based on a same cause for the boosting; and
cause, via a user interface, a display of an offer to view the partially viewed content item, based on the predictive factor.
7. The system of claim 6 , wherein the predictive factor is triggered by at least one of (a) a day and time combination associated with a user behavior associated with a particular content item, and (b) partially viewed duration time value associated with a particular content item.
8. The system of claim 6 , wherein the control circuitry is further configured to:
generate a candidate set of offers by determining the candidate set of offers to view one or more recorded content items available on a media device based, at least in part, on one or more predictive factors associated with the content including at least one or more of linear content, partially viewed content, over-the-top content, recorded asset content, content associated with a collection affinity value, or content associated with a genre affinity value; and
select the candidate set of offers based on a variety of metrics associated with each offer of the candidate set of offers.
9. The system of claim 8 , wherein the control circuitry is configured, when generating the candidate set of offers to view content, to:
determine a frequency of consumption rate based on user watching behavior associated with the series; and
based on the frequency of consumption rate, determine the candidate set of offers associated with the content including at least one or more of over-the-top content or recorded asset content, the content further comprising a next episode in the series.
10. The system of claim 8 , wherein the control circuitry is further configured to:
receive a user input associated with a presentation of at least one candidate offer via the user interface;
update one or more confidence values associated with the one or more predictive factors associated with the at least one candidate offer based on the user input.
11. The system of claim 6 , wherein the control circuitry is configured, when causing, via the user interface, the display of the offer to view the partially viewed content item, based on the predictive factor, to:
provide for display of the user interface a user interface screen including at least one of a feed, a carousel, or a notification screen.
12. A non-transitory computer-readable medium storing instructions, wherein the instructions, when executed by one or more processors, cause the one or more processors to perform:
determining that a content item was partially viewed;
in response to determining that the content item was partially viewed, boosting a predictive factor associated with the content item;
in response to determining that the content item is an episode of a series, wherein a number of episodes of the series were previously viewed, further boosting the predictive factor associated with the content item;
decaying, after the boosting, the predictive factor at a decay rate over a time period, wherein the time period begins when the partially viewed content item was partially viewed, wherein the decay rate is correlated with the boosting by determining the decay rate based on a same cause for the boosting; and
causing, via a user interface, a display of an offer to view the partially viewed content item, based on the predictive factor.
13. The non-transitory computer-readable medium of claim 12 , wherein the predictive factor is triggered by at least one of (a) a day and time combination associated with a user behavior associated with a particular content item, and (b) partially viewed duration time value associated with a particular content item.
14. The non-transitory computer-readable medium of claim 12 , wherein the instructions are further configured to perform:
generating a candidate set of offers by determining the candidate set of offers to view one or more recorded content items available on a media device based, at least in part, on one or more predictive factors associated with the content including at least one or more of linear content, partially viewed content, over-the-top content, recorded asset content, content associated with a collection affinity value, or content associated with a genre affinity value; and
selecting the candidate set of offers based on a variety of metrics associated with each offer of the candidate set of offers.
15. The non-transitory computer-readable medium of claim 14 , wherein the instructions, when generating the candidate set of offers to view content, further perform:
determining a frequency of consumption rate based on user watching behavior associated with the series; and
based on the frequency of consumption rate, determining the candidate set of offers associated with the content including at least one or more of over-the-top content or recorded asset content, the content further comprising a next episode in the series.
16. The non-transitory computer-readable medium of claim 14 , wherein the instructions are further configured to perform:
receiving a user input associated with a presentation of at least one offer candidate via the user interface;
updating one or more confidence values associated with the one or more predictive factors associated with the at least one candidate offer based on the user input.
17. The non-transitory computer-readable medium of claim 12 , wherein the instructions for causing, via the user interface, the display of the offer to view the partially viewed content item, based on the predictive factor further perform:
providing for display of the user interface a user interface screen including at least one of a feed, a carousel, or a notification screen.