Personalized delivery time optimization
View Patent ↗Techniques for optimizing a delivery time for the delivery of messages are described. According to various embodiments, a system determines, for each of a plurality of time intervals, a likelihood of a particular member of an online social network service performing a particular member user action on a particular message content item during the corresponding time interval. The plurality of time intervals are then ranked, based on the determined likelihoods corresponding to the plurality of time intervals. Thereafter, a particular time interval is identified from among the plurality of time intervals that is associated with a highest ranking. The particular time interval is then classified as an optimum personalized message delivery time for the particular member.
1. A method comprising:
determining, by a machine including a memory and at least one processor, for each of a plurality of time intervals, a likelihood of a first member of an online social network service performing a particular action on a particular message content item during the corresponding time interval by:
identifying a second member of the online social network service based on first member profile data of the first member,
receiving first geolocation data indicating a current location of the first member in real time from a client device of the first member,
determining a weight for the second member based on second member profile data of the second member, second geolocation data of the second member, the first member profile data, and the first geolocation data, and
determining the likelihood of the first member performing the particular action on the particular message content item during the corresponding time interval using the second member profile data, the second geolocation data and the determined weight;
ranking the plurality of time intervals, based on the determined likelihoods corresponding to the plurality of time intervals;
identifying a particular time interval from among the plurality of time intervals that is associated with a highest ranking;
classifying the particular time interval as an optimum personalized message delivery time for the first member; and
adjusting a message delivery preference associated with the first member based on the optimum personalized message delivery time.
2. The method of claim 1 , wherein each of the plurality of time intervals corresponds to a particular hour of the day.
3. The method of claim 1 , wherein each of the plurality of time intervals corresponds to a particular day of the week.
4. The method of claim 1 , wherein the optimum personalized message delivery time corresponds to a second time interval that includes the particular time interval.
5. The method of claim 1 , wherein the particular action is any one of a click response, a non-click response, and a conversion response.
6. The method of claim 1 , wherein the message content item corresponds to at least one of an email message, a text message, a social network instant message, and a chat message.
7. The method of claim 1 , further comprising transmitting a message to the first member at the optimum personalized message delivery time, based on the adjusted message delivery preference associated with the first member.
8. The method of claim 1 , wherein the message delivery preference corresponds to at least one of a frequency of message delivery and a message content.
9. The method of claim 1 , further comprising causing presentation of the adjusted message delivery preference on a display device associated with the first member.
10. The method of claim 1 , further comprising:
inferring a time zone corresponding to the current location of the first member; and
adjusting the optimum personalized message delivery time according to the determined time zone.
11. The method of claim 1 , wherein the weight is determined based on at least one of a degree of connectedness between the second member and the first member on the online social network service, a strength of connection between the second member and the first member, or a similarity between the first member profile data and the second member profile data.
12. A system comprising:
a processor, and a memory including instructions, which when executed by the processor, cause the processor to:
determine, for each of a plurality of time intervals, a likelihood of a first member of an online social network service performing a particular action on a particular message content item during the corresponding time interval by:
identify a second member of the online social network service based on first member profile data of the first member,
receive first geolocation data indicating a current location of the first member in real time from a client device of the first member,
determine a weight for the second member based on second member profile data of the second member, second geolocation data of the second member, the first member profile data, and the first geolocation data, and
determine the likelihood of the first member performing the particular action on the particular message content item during the corresponding time interval using the second member profile data, the second geolocation data and the determined weight;
rank the plurality of time intervals, based on the determined likelihood corresponding to the plurality of time intervals;
identify a particular time interval from among the plurality of time intervals that is associated with a highest ranking;
classify the particular time interval as an optimum personalized message delivery time for the first member; and
adjust a message delivery preference associated with the first member based on the optimum personalized message delivery time.
13. A non-transitory machine-readable storage medium comprising instructions that, when executed by one or more processors of a machine, cause the machine to perform operations comprising:
determining, for each of a plurality of time intervals, a likelihood of a first member of an online social network service performing a particular action on a particular message content item during the corresponding time interval by:
identifying a second member of the online social network service based on first member profile data of the first member,
receiving first geolocation data indicating a current location of the first member in real time from a client device of the first member,
determining a weight for the second member based on second member profile data of the second member, second geolocation data of the second member, the first member profile data, and the first geolocation data, and
determining the likelihood of the first member performing the particular action on the particular message content item during the corresponding time interval using the second member profile data, the second geolocation data and the determined weight;
ranking the plurality of time intervals, based on the determined likelihoods corresponding to the plurality of time intervals;
identifying a particular time interval from among the plurality of time intervals that is associated with a highest ranking;
classifying the particular time interval as an optimum personalized message delivery time for the first member; and
adjusting a message delivery preference associated with the first member based on the optimum personalized message delivery time.