Machine learning models for adjusting communication parameters

1. A method performed by one or more computers, the method comprising:

obtaining, by the one or more computers, data for each communication device in a set of multiple communication devices, the data for each communication device indicating (i) a communication setting used by the communication device, (ii) an efficiency measure for communication by the communication device using the communication setting, and (iii) a geographic location of the communication device;

training, by the one or more computers, a machine learning model based on the obtained data to receive an indication of a geographic location and predict a communication setting capable of providing at least a minimum level of efficiency for communication at the geographic location;

after training the machine learning model, generating, using the machine learning model, an indication of a predicted communication setting for a particular communication device, the predicted communication setting being predicted by the trained machine learning model to provide at least the minimum level of efficiency for communication at a particular geographic location where the particular communication device is located; and

determining, by the one or more computers, whether to change a current communication setting for the particular communication device based on the predicted communication setting.

2. The method of claim 1 , wherein the machine learning model is trained to indicate, from among multiple communication settings, a communication setting predicted to provide a highest efficiency of communication based on input to the machine learning model that includes an indication of the particular geographic location.

3. The method of claim 1 , wherein, in the obtained data for the multiple communication devices, the efficiency measure is determined based on a modulation or coding used by the communication device.

4. The method of claim 1 , wherein, in the obtained data for the multiple communication devices, the efficiency measure is determined based on a compression ratio for the communication device or an end-to-end traffic response time for the communication device.

5. The method of claim 1 , wherein the efficiency measure for a communication device indicates a number of bits per symbol transferred using the communication setting assigned to the communication device.

6. The method of claim 1 , wherein the machine learning model is trained to predict a satellite beam for a communication device to use, such that the predicted communication setting is a predicted satellite beam.

7. The method of claim 1 , wherein the machine learning model is trained to predict a cell assignment for a communication device to use, such that the predicted communication setting is a predicted cell assignment.

8. The method of claim 1 , wherein the machine learning model is trained to predict a data rate for a communication device to use, such that the predicted communication setting is a predicted data rate.

9. The method of claim 1 , wherein the machine learning model is trained to predict a wireless communication channel for a communication device to use, such that the predicted communication setting is a predicted wireless communication channel.

10. The method of claim 1 , wherein the machine learning model is trained to predict a modulation for a communication device to use, such that the predicted communication setting is a predicted modulation.

11. The method of claim 1 , wherein the machine learning model is trained to predict an encoding for a communication device to use, such that the predicted communication setting is a predicted encoding.

12. The method of claim 1 , wherein determining whether to change the current communication setting comprises determining to assign the predicted communication setting to the particular communication device; and

wherein the method includes initiating a change of the communication setting for the communication device from a current communication setting of the particular communication device to the predicted communication setting.

13. The method of claim 1 , wherein training the machine learning model comprises:

identifying a subset of the multiple communication devices that have an efficiency measure that satisfies a threshold; and

using the data for the identified subset of the multiple communication devices as training examples for training the machine learning model;

wherein the method comprises, after training the machine learning model, using the trained machine learning model to determine a predicted communication setting for each of the communication devices that have efficiency measures that do not satisfy the threshold.

14. The method of claim 1 , wherein the machine learning model is a first machine learning model;

wherein the method further comprises training a second machine learning model based on the obtained data for the multiple communication devices, wherein the first machine learning model and the second machine learning model operates using a different predictive algorithm; and

wherein the indication of a predicted communication setting for the particular geographic location is generated using output of the first machine learning model and the second machine learning model.

15. The method of claim 1 , wherein the machine learning model comprises a neural network, a maximum entropy classifier, a decision tree, an XG boost tree, a random forest classifier, a support vector machine, or a logistic regression model.

16. The method of claim 1 , wherein training the machine learning model comprises training the machine learning model to predict a communication setting for a communication device based on receiving only an indication of the geographic location of the communication device as input;

wherein generating the indication of the predicted communication setting for the particular geographic location comprises:

providing data indicating the particular geographic location as input to the trained machine learning model; and

receiving, as output of the trained machine learning model, data indicating the predicted communication setting for the particular geographic location.

17. The method of claim 1 , further comprising training multiple different machine learning models for different sets of communication settings, wherein the machine learning model for a set of communication settings is trained based on data describing communication devices currently assigned to use one of the communication settings in the set.

18. A system comprising:

one or more computers; and

one or more computer-readable media storing instructions that, when executed by the one or more computers, cause the one or more computers to perform operations comprising:

obtaining, by the one or more computers, data for each communication device in a set of multiple communication devices, the data for each communication device indicating (i) a communication setting used by the communication device, (ii) an efficiency measure for communication by the communication device using the communication setting, and (iii) a geographic location of the communication device;

training, by the one or more computers, a machine learning model based on the obtained data to receive an indication of a geographic location and predict a communication setting capable of providing at least a minimum level of efficiency for communication at the geographic location;

after training the machine learning model, generating, using the machine learning model, an indication of a predicted communication setting for a particular communication device, the predicted communication setting being predicted by the trained machine learning model to provide at least the minimum level of efficiency for communication at a particular geographic location where the particular communication device is located; and

determining, by the one or more computers, whether to change a current communication setting for the particular communication device based on the predicted communication setting.

19. The system of claim 18 , wherein the machine learning model is trained to select, from among multiple communication settings, a communication setting providing a highest efficiency of communication for the geographic location indicated to the machine learning model.

20. One or more non-transitory computer-readable media storing instructions that, when executed by one or more computers, cause the one or more computers to perform operations comprising:

obtaining, by the one or more computers, data for each communication device in a set of multiple communication devices, the data for each communication device indicating (i) a communication setting used by the communication device, (ii) an efficiency measure for communication by the communication device using the communication setting, and (iii) a geographic location of the communication device;

training, by the one or more computers, a machine learning model based on the obtained data to receive an indication of a geographic location and predict a communication setting capable of providing at least a minimum level of efficiency for communication at the geographic location;

after training the machine learning model, generating, using the machine learning model, an indication of a predicted communication setting for a particular communication device, the predicted communication setting being predicted by the trained machine learning model to provide at least the minimum level of efficiency for communication at a particular geographic location where the particular communication device is located; and

determining, by the one or more computers, whether to change a current communication setting for the particular communication device based on the predicted communication setting.