PERSONALIZED DELIVERY TIME OPTIMIZATION

• US 20170026331A1
• Filed: 10/10/2016
• Published: 01/26/2017
• Est. Priority Date: 06/30/2014
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: LinkedIn Corporation (Microsoft Corporation)
• Inventors: Vijay, Ravi Kiran Holur, Arai, Benjamin, Hull, Mark, Irmak, Utku, Khincha, Pramod Chand, Shah, Samir M., Yan, Ji, Yuan, Lawrence
• Granted Patent: US 9,967,226 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/335 Filtering based on additional data, e.g. user or group profiles filtering in web context G06F16/9535, G06F16/9536
• CPC Class Codes: G06F 16/487 using geographical or spatial information, e.g. location
• CPC Class Codes: G06F 16/735 Filtering based on additional data, e.g. user or group profiles
• CPC Class Codes: G06Q 10/107 Computer-aided management of electronic mailing [e-mailing]
• CPC Class Codes: G06Q 50/01 Social networking
• CPC Class Codes: H04L 41/147 for predicting network behaviour
• CPC Class Codes: H04L 43/08 Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
• CPC Class Codes: H04L 51/214 using selective forwarding
• CPC Class Codes: H04L 51/222 using geographical location information, e.g. messages transmitted or received in proximity of a certain spot or area
• CPC Class Codes: H04L 51/226 Delivery according to priorities
• CPC Class Codes: H04L 51/52 for supporting social networking services
• CPC Class Codes: H04L 63/102 Entity profiles
• CPC Class Codes: H04L 67/306 User profiles

Abstract

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.

Claims

1. A computer-implemented 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 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;

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; and

classifying the particular time interval as an optimum personalized message delivery time for the particular member;

wherein the determining comprises;

accessing, via one or more data sources, data including email content data describing a particular email content item and member email interaction data describing the particular member'"'"'s interactions with various email content;

encoding the data accessed from the external data sources into one or more feature vectors, and assembling the one or more feature vectors to thereby generate an assembled feature vector; and

performing prediction modeling, based on the assembled feature vector and a trained prediction model, to predict the likelihood of the particular member performing the particular user action on the particular email content item.

2. The method of claim 1, further comprising:

determining a time zone associated with a current location of the particular member; and

encoding the time zone into the assembled feature vector.

3. The method of claim 1, wherein the email content data specifies an email type, and wherein the email type is at least one of a network connection update e-mail, a news update e-mail, a jobs update e-mail, an influencer post update e-mail, a company update e-mail, a group update e-mail, a university update e-mail, and a digest e-mail.

4. The method of claim 1, wherein the member email interaction data indicates a quantity of various email types transmitted to the particular member, a quantity of clicks submitted by the particular member in conjunction with the various email types, and a quantity of email unsubscribe requests submitted by the particular member in conjunction with the various email types.

5. The method of claim 1, further comprising:

accessing, via one or more data sources, member site interaction data describing the particular member'"'"'s interaction with various features or content of an online social network service; and

encoding the member site interaction data into the assembled feature vector.

6. The method of claim 1, further comprising:

accessing, via one or more data sources, member profile data describing the particular member; and

encoding the member profile data into the assembled feature vector.

7. The method of claim 1, wherein the prediction model is any one of a logistic regression model, a Naï

ve Bayes model, a support vector machines (SVM) model, a decision trees model, and a neural network model.

8. The method of claim 1, wherein the prediction modeling comprises a training operation to refine coefficients of a logistic regression model, based on training set data comprising the assembled feature vector.

9. A system comprising:

a processor; and

a memory comprising instructions that, when executed by the processor, cause the system to;

determine, 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;

rank the plurality of time intervals, based on the determined likelihoods 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; and

classify the particular time interval as an optimum personalized message delivery time for the particular member;

wherein to determine the likelihood, the memory comprises instructions that, when executed by the processor, cause the system to;

access, via one or more data sources, data including email content data describing a particular email content item and member email interaction data describing the particular member'"'"'s interactions with various email content;

encode the data accessed from the external data sources into one or more feature vectors, and assembling the one or more feature vectors to thereby generate an assembled feature vector; and

perform prediction modeling, based on the assembled feature vector and a trained prediction model, to predict the likelihood of the particular member performing the particular user action on the particular email content item.

10. The system of claim 9, further comprising instructions that, when executed by the processor, cause the system to:

determine a time zone associated with a current location of the particular member; and

encode the time zone into the assembled feature vector.

11. The system of claim 9, wherein the email content data specifies an email type, and wherein the email type is at least one of a network connection update e-mail, a news update e-mail, a jobs update e-mail, an influencer post update e-mail, a company update e-mail, a group update e-mail, a university update e-mail, and a digest e-mail.

12. The system of claim 9, wherein the member email interaction data indicates a quantity of various email types transmitted to the particular member, a quantity of clicks submitted by the particular member in conjunction with the various email types, and a quantity of email unsubscribe requests submitted by the particular member in conjunction with the various email types.

13. The system of claim 9, further comprising instructions that, when executed by the processor, cause the system to:

access, via one or more data sources, member site interaction data describing the particular member'"'"'s interaction with various features or content of an online social network service; and

encode the member site interaction data into the assembled feature vector.

14. The system of claim 9, further comprising instructions that, when executed by the processor, cause the system to:

access, via one or more data sources, member profile data describing the particular member; and

encode the member profile data into the assembled feature vector.

15. The system of claim 9, wherein the prediction model is any one of a logistic regression model, a Naï

ve Bayes model, a support vector machines (SVM) model, a decision trees model, and a neural network model.

16. The system of claim 9, wherein the prediction modeling comprises a training operation to refine coefficients of a logistic regression model, based on training set data comprising the assembled feature vector.

17. 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 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;

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; and

classifying the particular time interval as an optimum personalized message delivery time for the particular member;

wherein the determining comprises;

accessing, via one or more data sources, data including email content data describing a particular email content item and member email interaction data describing the particular member'"'"'s interactions with various email content;

encoding the data accessed from the external data sources into one or more feature vectors, and assembling the one or more feature vectors to thereby generate an assembled feature vector; and

performing prediction modeling, based on the assembled feature vector and a trained prediction model, to predict the likelihood of the particular member performing the particular user action on the particular email content item.

18. The storage medium of claim 17, the operations further comprising:

determining a time zone associated with a current location of the particular member; and

encoding the time zone into the assembled feature vector.

19. The storage medium of claim 17, the operations further comprising:

accessing, via one or more data sources, member site interaction data describing the particular member'"'"'s interaction with various features or content of an online social network service; and

encoding the member site interaction data into the assembled feature vector.

20. The storage medium of claim 17, the operations further comprising:

accessing, via one or more data sources, member profile data describing the particular member; and

encoding the member profile data into the assembled feature vector.