Systems and methods for dynamically augmenting machine learning models based on contextual factors associated with execution environments

1. A computer-implemented method for dynamically augmenting machine learning models based on contextual factors associated with execution environments, at least a portion of the method being performed by a computing device comprising at least one processor, the computer-implemented method comprising:

generating a base machine learning model and a set of supplemental machine learning models;

determining at least one contextual factor associated with an execution environment of a machine learning system that is configured to make predictions regarding a set of input data using at least the base machine learning model;

selecting, based on the contextual factor associated with the execution environment of the machine learning system, a continuation set of machine learning models from the set of supplemental machine learning models;

directing the machine learning system to utilize both the base machine learning model and the continuation set of machine learning models when making the predictions regarding the set of input data; and

predicting, using the machine learning system, that malware is present on a source computing device.

2. The computer-implemented method of claim 1 , wherein the contextual factor associated with the execution environment of the machine learning system comprises at least one of:

a performance profile associated with the execution environment;

processing resources of the execution environment;

memory resources of the execution environment;

bandwidth resources of the execution environment;

a machine type associated with the execution environment;

a hardware designator associated with the execution environment; and

a software environment of the execution environment.

3. The computer-implemented method of claim 1 , wherein:

the base machine learning model comprises a random forest comprising at least one decision tree; and

the continuation set of machine learning models comprises at least one additional decision tree.

4. The computer-implemented method of claim 3 , wherein directing the machine learning system to utilize both the base machine learning model and the continuation set of machine learning models when making the predictions regarding the set of input data comprises including the additional decision tree in the random forest when making the predictions regarding the set of input data.

5. The computer-implemented method of claim 1 , wherein selecting the continuation set of machine learning models comprises determining, based on the contextual factor, that the machine learning system is capable of making the predictions regarding input data within a threshold period of time while utilizing both the base machine learning model and the continuation set of machine learning models.

6. The computer-implemented method of claim 1 , wherein selecting the continuation set of machine learning models comprises:

identifying a prediction improvement factor associated with a machine learning model included in the set of supplemental machine learning models;

determining that the prediction improvement factor associated with the machine learning model is greater than a predetermined prediction improvement threshold; and

including the machine learning model in the continuation set of machine learning models.

7. The computer-implemented method of claim 1 , wherein selecting the continuation set of machine learning models comprises:

selecting at least one decision tree from a set of decision trees included in the set of supplemental machine learning models; and

designating the decision tree as at least part of the continuation set of machine learning models.

8. The computer-implemented method of claim 1 , wherein generating the base machine learning model and the set of supplemental machine learning models comprises:

identifying a base set of attributes included in a set of training data and a supplemental set of attributes included in the set of training data;

generating the base machine learning model based on the base set of attributes included in the set of training data;

generating at least one supplemental machine learning model based on the supplemental set of attributes included in the set of training data; and

including the supplemental machine learning model in the set of supplemental machine learning models.

9. The computer-implemented method of claim 8 , wherein:

generating the base machine learning model comprises generating a random forest based on the set of training data and the base set of attributes;

generating the supplemental machine learning model comprises:

generating a supplemental decision tree based on the set of training data and at least one attribute included in the supplemental set of attributes; and

including the supplemental decision tree in the supplemental machine learning model;

selecting the continuation set of machine learning models from the set of supplemental machine learning models comprises selecting the supplemental machine learning model; and

directing the machine learning system to utilize both the base machine learning model and the continuation set of machine learning models when making the predictions regarding the set of input data comprises including the supplemental decision tree in the random forest when making the predictions regarding the set of input data.

10. The computer-implemented method of claim 1 , wherein:

the machine learning system is further configured to utilize both the base machine learning model and the continuation set of machine learning models to make predictions regarding whether data corresponds to malware properties; and

the set of input data corresponds to the malware properties.

11. The computer-implemented method of claim 1 , further comprising performing a security action to protect the source computing device from the malware predicted to be present on the source computing device.

12. The computer-implemented method of claim 11 , wherein the security action comprises at least one of:

notifying an administrator of the source computing device that the malware may be present on the source computing device;

preventing a user from accessing the malware;

quarantining the malware within a secure storage location;

preventing the source computing device from transmitting the malware to another computing device; and

preventing the source computing device from transmitting the malware to the another computing device by shutting down the source computing device.

13. A system for dynamically augmenting machine learning models based on contextual factors associated with execution environments, the system comprising:

a generation module, stored in memory, that generates a base machine learning model and a set of supplemental machine learning models;

a determination module, stored in memory, that determines at least one contextual factor associated with an execution environment of a machine learning system that is configured to make predictions regarding a set of input data using at least the base machine learning model;

a selection module, stored in memory, that selects, based on the contextual factor associated with the execution environment of the machine learning system, a continuation set of machine learning models from the set of supplemental machine learning models;

a direction module, stored in memory, that directs the machine learning system to utilize both the base machine learning model and the continuation set of machine learning models when making the predictions regarding the set of input data, wherein the machine learning system predicts that malware is present on a source computing device; and

at least one physical processor that executes the generation module, the determination module, the selection module, and the direction module.

14. The system of claim 13 , wherein the contextual factor associated with the execution environment of the machine learning system comprises at least one of:

a performance profile associated with the execution environment;

processing resources of the execution environment;

memory resources of the execution environment;

bandwidth resources of the execution environment;

a machine type associated with the execution environment;

a hardware designator associated with the execution environment; and

a software environment of the execution environment.

15. The system of claim 13 , wherein:

the base machine learning model comprises a random forest comprising at least one decision tree;

the continuation set of machine learning models comprises at least one additional decision tree; and

the direction module directs the machine learning system to utilize both the base machine learning model and the continuation set of machine learning models when making the predictions regarding the set of input data by including the additional decision tree in the random forest when making the predictions regarding the set of input data.

16. The system of claim 13 , wherein the selection module selects the continuation set of machine learning models by determining, based on the contextual factor, that the machine learning system is capable of making the predictions regarding input data within a threshold period of time while utilizing both the base machine learning model and the continuation set of machine learning models.

17. The system of claim 13 , wherein the selection module selects the continuation set of machine learning models by:

selecting at least one decision tree from a set of decision trees included in the set of supplemental machine learning models; and

designating the decision tree as at least part of the continuation set of machine learning models.

18. The system of claim 13 , wherein:

the machine learning system is further configured to utilize both the base machine learning model and the continuation set of machine learning models to make predictions regarding whether data corresponds to malware properties; and

the set of input data corresponds to the malware properties.

19. A non-transitory computer-readable medium comprising one or more computer-executable instructions that, when executed by at least one processor of a computing device, cause the computing device to:

generate a base machine learning model and a supplemental set of machine learning models;

determine at least one contextual factor associated with an execution environment of a machine learning system that is configured to make predictions regarding a set of input data using at least the base machine learning model;

select, based on the contextual factor associated with the execution environment of the machine learning system, a continuation set of machine learning models from the supplemental set of machine learning models;

direct the machine learning system to utilize both the base machine learning model and the continuation set of machine learning models when making the predictions regarding the set of input data; and

predict, using the machine learning system, that malware is present on a source computing device.

20. The medium of claim 19 , wherein the contextual factor associated with the execution environment of the machine learning system comprises at least one of:

a performance profile associated with the execution environment;

processing resources of the execution environment;

memory resources of the execution environment;

bandwidth resources of the execution environment;

a machine type associated with the execution environment;

a hardware designator associated with the execution environment; and

a software environment of the execution environment.