CUSTOMIZED PREDICTORS FOR USER ACTIONS IN AN ONLINE SYSTEM

• US 20140156566A1
• Filed: 11/30/2012
• Published: 06/05/2014
• Est. Priority Date: 11/30/2012
• Status: Active Grant

• Current Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Original Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Inventors: Hua, Ming, Yan, Hong, Kabiljo, Igor, Ilic, Aleksandar
• Granted Patent: US 9,317,812 B2
• Time in Patent Office: Days
• US Class Current: 706/12
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

Online systems generate predictors for predicting actions of users of the online system. The online system receives requests to generate predictor models for predicting whether a user is likely to take an action of a particular action type. The request specifies the type of action and criteria for identifying a successful instance of the action type and a failure instance of the action type. The online system collects data including successful and failure instances of the action type. The online system generates one or more predictors of different types using the generated data. The online system evaluates and compares the performance of the different predictors generated and selects a predictor based on the performance. The online system returns a handle to access the generated predictor to the requester of the predictor.

Claims

1. A computer-implemented method comprising:

receiving, by an online system, a plurality of requests for generating predictors, each request specifying a type of action performed by users of the online system and criteria for identifying a successful instance of the type of action;

for each request associated with a type of action, generating, by the online system, a predictor for the type of action, the generating comprising;

identifying a training data set comprising a plurality of successful instances and a plurality of failure instances of the type of action performed by users of the online system;

training one or more candidate predictors using the identified data set, wherein each candidate predictor comprises a machine learned model;

evaluating performance of each candidate predictor by executing each predictor on a test data set comprising a plurality of successful instances and a plurality of failure instances of the type of action performed by users of the online system; and

selecting a predictor for the type of action by comparing the performance of the one or more candidate predictors; and

returning a handle corresponding to the generated predictor to a requester of the selected predictor.

2. The computer-implemented method of claim 1, further comprising:

receiving a request for a predictor from a process running in the online system, the request specifying a handle and an instance of user information;

executing the predictor corresponding to the specified handle on the instance of user information; and

returning a result of the predictor to the requesting process.

3. The computer-implemented method of claim 1, wherein a successful instance of a type of action corresponds to information stored in the online system indicating a user taking an action of the type responsive to the user being presented with a user interface that allows users to take actions of the type of action.

4. The computer-implemented method of claim 1, wherein the request further specifies criteria for failure instance, wherein a failure instance of a type of action corresponds to information stored in the online system indicating a user'"'"'s failure to take an action of the type responsive to the user being presented with information that allows the user to take action of the type of action.

5. The computer-implemented method of claim 4, wherein a failure instance of a type of action corresponds to information stored in the online system indicating a user providing input indicating a dislike for information presented in a user interface associated with the type of action.

6. The computer-implemented method of claim 1, wherein each type of action is targeted to an entity represented in the online system.

7. The computer-implemented method of claim 6, wherein the entity corresponding to the type of action is one of a user of the online system, a social group, or an image.

8. The computer-implemented method of claim 1, wherein a candidate predictor is a machine learning model of a type based on one of a linear regression, a logistic regression, boosting tree, or weighted decision tree.

9. The computer-implemented method of claim 1, further comprising, for each generated predictor for a type of action:

comparing performance of the generated predictor against performance of an existing predictor of the type of action; and

responsive to the performance of the generated predictor exceeding the performance of the existing predictor, replacing the existing predictor with the generated predictor.

10. The computer-implemented method of claim 9, further comprising, for each type of action, periodically generating a new predictor:

comparing performance of the new predictor against performance of a previously generated predictor; and

responsive to the performance of the new predictor exceeding the performance of the previously generated predictor, replacing the previously generated predictor with the new predictor.

11. The computer-implemented method of claim 10, wherein a rate of periodically generating new predictors for each action type is determined based on a comparison of performance of the new predictors with performance of previously generated predictors.

12. The computer-implemented method of claim 11, wherein the rate of periodically generating new predictors for each action type is reduced responsive to an improvement in performance of the new predictor compared to the performance of the existing predictor being below a threshold value.

13. A computer-implemented method comprising:

storing, by an online system, a plurality of predictors, each predictor for predicting whether a user of the online system performs a type of action, each predictor associated with criteria for determining a successful instance of the type of action;

selecting an existing predictor corresponding to a type of action;

identifying a data set comprising successful instances and failure instances of the type of action performed by users of the online system;

training one or more candidate predictors using the identified data set, wherein each candidate predictor comprises a machine learned model;

evaluating performance of each candidate predictor by executing each predictor on a test data set comprising a plurality of successful instances and a plurality of failure instances of the type of action performed by users of the online system;

selecting a candidate predictor from the one or more candidate predictors by comparing the performance of the one or more candidate predictors;

comparing performance of the selected candidate predictor with performance of the existing predictors; and

replacing the existing predictor by the selected candidate predictor responsive to performance of the selected candidate predictor exceeding the performance of the existing predictor.

14. The computer-implemented method of claim 13, wherein a successful instance of a type of action corresponds to information stored in the online system indicating a user taking an action of the type responsive to the user being presented with a user interface that allows users to take actions of the type of action.

15. The computer-implemented method of claim 13, wherein a failure instance of a type of action corresponds to information stored in the online system indicating a user failing to take an action of the type responsive to the user being presented with a user interface that allows users to take actions of the type of action.

16. The computer-implemented method of claim 13, wherein a candidate predictor is a machine learning model of a type based on one of a linear regression, a logistic regression, boosting tree, or weighted decision tree.

17. The computer-implemented method of claim 13, further comprising, periodically generating a new predictor:

comparing performance of the new predictor against performance of a previously generated predictor; and

responsive to the performance of the new predictor exceeding the performance of the previously generated predictor, replacing the previously generated predictor with the new predictor.

18. The computer-implemented method of claim 17, wherein a rate of periodically generating new predictors for each action type is reduced responsive to an improvement in performance of the new predictor compared to the performance of the existing predictor being below a threshold value.

19. A computer program product having a non-transitory computer-readable storage medium storing computer-executable code, the code comprising:

a predictor factory module of an online system configured to;

store a plurality of predictors, each predictor for predicting whether a user of the online system performs a type of action, each predictor associated with criteria for determining a successful instance of the type of action;

select an existing predictor corresponding to a type of action;

identify a data set comprising successful instances and failure instances of the type of action performed by users of the online system;

train one or more candidate predictors using the identified data set, wherein each candidate predictor comprises a machine learned model;

evaluate performance of each candidate predictor by executing each predictor on a test data set comprising a plurality of successful instances and a plurality of failure instances of the type of action performed by users of the online system;

select a candidate predictor from the one or more candidate predictors by comparing the performance of the one or more candidate predictors;

compare performance of the selected candidate predictor with performance of the existing predictors; and

replace the existing predictor by the selected candidate predictor responsive to performance of the selected candidate predictor exceeding the performance of the existing predictor.

20. The computer program product of claim 19, wherein a successful instance of a type of action corresponds to information stored in the online system indicating a user taking an action of the type responsive to the user being presented with a user interface that allows users to take actions of the type of action.

21. The computer program product of claim 19, wherein a failure instance of a type of action corresponds to information stored in the online system indicating a user failing to take an action of the type responsive to the user being presented with a user interface that allows users to take actions of the type of action.