Probabilistic message distribution

Patent metadata

Field	Value
Publication number	US-2017098169-A1
Application number	US-201514874201-A
Country	US
Kind code	A1
Filing date	Oct 2, 2015
Priority date	Oct 2, 2015
Publication date	Apr 6, 2017
Grant date	—

Abstract

This disclosure relates to systems and methods that include configuring a machine learning system to train on a plurality of messages, solving, for a set of input messages, a multi-objective optimization problem to minimize a number of messages to send while satisfying one or more constraints, selecting a random value for a message in the set, setting a send constraint for the message in the set using the send threshold for the message in the set and the random value, and sending the message in the set in response to the send constraint being satisfied.

First claim

What is claimed is:

1 . A system comprising:
a machine-readable medium having instructions stored thereon, which, when executed by a processor, cause the system to: configure a machine learning system to train on a plurality of messages, the machine learning system outputting an expected number of positive responses based on an input message and an expected number of negative responses based on the input message; solve, for a set of input messages, a multi-objective optimization problem to minimize a number of messages to send while satisfying one or more constraints, the multi-objective optimization problem including the expected number of positive responses and the expected number of negative responses for each message in the set, the solving resulting in a send threshold for each message in the set; select a random value for a message in the set; set a send constraint for the message in the set using the send threshold for the message in the set and the random value; and send the message in the set in response to the send constraint being satisfied.

2 . The system of claim 1 , wherein the one or more constraints includes the summation of send probabilities being below a threshold number.

3 . The system of claim 1 , wherein the one or more constraints includes the expected number of negative responses being below a threshold number.

4 . The system of claim 1 , wherein solving the multi-objective optimization problem comprises solving the multi-objective optimization problem for two or more different time periods resulting in send probabilities for each of the message for each of the different time periods, the random value selected to indicate one of the different time periods using the send probabilities for the message.

5 . The system of claim 1 , wherein solving the multi-objective optimization problem comprises solving the multi-objective optimization problem for two or more different transmission channels resulting in send probabilities for each of the messages and each of the two or more different transmission channel, the random value selected to indicate one of the two or more different transmission channels based on the send constraint, the sending using the indicated transmission channel.

6 . The system of claim 1 , wherein satisfying the send constraint for a message comprises the random number being lower than the send threshold.

7 . The system of claim 1 , wherein one or more of the positive responses is selected from the group consisting of a page view, a clicked link, a purchase, a like, and a comment, and one or more of the negative responses is selected from the group consisting of an unsubscribe, a complaint, a dislike, and a spam report.

8 . The system of claim 1 , wherein the machine learning system is configured to train on a user's activity for a threshold period of time based on a response to one of the plurality of messages.

9 . A method comprising:
configuring a machine learning system to train on a plurality of messages, the machine learning system outputting an expected number of positive responses based on an input message and an expected number of negative responses based on the input message; solving, for a set of input messages, a multi-objective optimization problem to minimize a summation of send probabilities for the messages in the set while satisfying one or more constraints, the multi-objective optimization problem including the expected number of positive responses and the expected number of negative responses for each message in the set, the solving resulting in a send threshold for each message in the set; selecting a random value for one of the one or more messages in the set; setting a send constraint for the message in the set using the send threshold and the random value; and sending messages in the set in response to the send constraint being satisfied.

10 . The method of claim 9 , wherein the one or more constraints includes the summation of send probabilities being below a threshold number.

11 . The method of claim 9 , wherein the one or more constraints includes the expected number of negative responses being below a threshold number.

12 . The method of claim 9 , wherein solving the multi-objective optimization problem comprises solving the multi-objective optimization problem for two or more different time periods resulting in send probabilities for each of the message for each of the different time periods, the random value selected to indicate one of the different time periods using the send probabilities for the message.

13 . The method of claim 9 , wherein solving the multi-objective optimization problem comprises solving the multi-objective optimization problem for two or more different transmission channels resulting in send probabilities for each of the messages and each of the two or more different transmission channel, the random value selected to indicate one of the two or more different transmission channels based on the send constraint, the sending using the indicated transmission channel.

14 . The method of claim 9 , wherein satisfying the send constraint for a message comprises the random number being lower than the send threshold.

15 . The method of claim 9 , wherein one or more of the positive responses is selected from the group consisting of a page view, a clicked link, a purchase, a like, and a comment, and one or more of the negative responses is selected from the group consisting of an unsubscribe, a complaint, a dislike, and a spam report.

16 . The method of claim 9 , wherein the machine learning system is configured to train on a user's activity for a threshold period of time based on a response to one of the plurality of messages.

17 . The method of claim 9 , wherein satisfying the send constraint for a message comprises the random number exceeding the value of one minus the send threshold.

18 . A non-transitory machine-readable medium having instructions stored thereon, which, when executed by a processor, cause the system to:
configure a machine learning system to train on a plurality of messages, the machine learning system outputting an expected number of positive responses based on an input message and an expected number of negative responses based on the input message; solve, for a set of input messages, a multi-objective optimization problem to minimize a number of messages to send while satisfying one or more constraints, the multi-objective optimization problem including the expected number of positive responses and the expected number of negative responses for each message in the set, the solving resulting in a send threshold for each message in the set; select a random value for a message in the set; set a send constraint for the message in the set using the send threshold for the message in the set and the random value; and send the message in the set in response to the send constraint being satisfied.

19 . The system of claim 18 , wherein solving the multi-objective optimization problem comprises solving the multi-objective optimization problem for two or more different time periods resulting in send probabilities for each of the message for each of the different time periods, the random value selected to indicate one of the different time periods using the send probabilities for the message.

20 . The system of claim 18 , wherein solving the multi-objective optimization problem comprises solving the multi-objective optimization problem for two or more different transmission channels re

Assignees

• Linkedin Corp

Inventors

• Gupta Rupesh
• Tseng Hsiao-Ping
• Vijay Ravi Kiran Holur
• Rosales Romer E

Classifications

• G06Q10/40

  Business processes related to social networking or social networking services · CPC title

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• G06Q10/107

  Computer-aided management of electronic mailing [e-mailing] · CPC title

• G06Q10/10

  Office automation; Time management · CPC title

• H04L51/32

  Electricity · mapped topic