Utilizing machine learning models to determine customer care actions for telecommunications network providers

1. A method, comprising:

receiving, by a device and from a monitoring device, anonymized historical telecommunications data associated with a telecommunications network that is monitored with the monitoring device,

wherein the monitoring device is a separate device from the device,

wherein the monitoring device is configured to perform a set of test logins using a set of usernames and passwords,

wherein the set of usernames and passwords is anonymized to create the anonymized historical telecommunications data,

wherein the monitoring device is configured to determine a customer care action to resolve a technical issue with the telecommunications network, and

wherein the monitoring device is configured to cause the customer care action to be implemented in the telecommunications network;

training, by the device, a plurality of machine learning models with the anonymized historical telecommunications data to generate a plurality of trained machine learning models;

generating, by the device, accuracy scores for the plurality of trained machine learning models based on training the plurality of machine learning models;

selecting, by the device, an optimum machine learning model, from the plurality of trained machine learning models, based on the accuracy scores for the plurality of trained machine learning models; and

providing, by the device, the optimum machine learning model to the monitoring device associated with the telecommunications network,

wherein the optimum machine learning model causes the monitoring device to:

process real time telecommunications data of the telecommunications network, with the optimum machine learning model, to determine the customer care action for the telecommunications network, and

cause the customer care action to be applied to an end customer utilizing a service provided by a telecommunications provider associated with the telecommunications network.

2. The method of claim 1 , wherein the anonymized historical telecommunications data includes one or more of:

anonymized historical customer premise equipment data associated with the telecommunications network,

anonymized historical network device inventory data associated with the telecommunications network, or

anonymized historical customer call data associated with the telecommunications network.

3. The method of claim 1 , wherein the anonymized historical telecommunications data is encrypted, compressed, and anonymized to remove data identifying a telecommunications network provider and customers of the telecommunications network provider.

4. The method of claim 1 , further comprising:

receiving feedback associated with the monitoring device implementing the optimum machine learning model with the telecommunications network; and

performing one or more actions based on the feedback.

5. The method of claim 4 , wherein performing the one or more actions comprises one or more of:

modifying the optimum machine learning model, based on the feedback and to generate a modified optimum machine learning model, and providing the modified optimum machine learning model to the monitoring device;

selecting another optimum machine learning model, from the plurality of machine learning models, based on the feedback, and providing the other optimum machine learning model to the monitoring device; or

retraining the plurality of machine learning models based on the feedback.

6. The method of claim 1 , wherein the monitoring device receives historical telecommunications data from the telecommunications network, and anonymizes the historical telecommunications data to generate the anonymized historical telecommunications data.

7. The method of claim 1 , wherein the plurality of machine learning models includes:

one or more random forest models,

one or more linear regression models, and

one or more neural network models.

8. A device, comprising:

one or more memories; and

one or more processors, communicatively coupled to the one or more memories, configured to:

receive, from a monitoring device, anonymized historical telecommunications data associated with a telecommunications network that is monitored with the monitoring device,

wherein the monitoring device is a separate device from the device,

wherein the monitoring device is configured to perform a set of test logins using a set of usernames and passwords,

wherein the set of usernames and passwords is anonymized to create the anonymized historical telecommunications data,

wherein the monitoring device is configured to determine a customer care action to resolve a technical issue with the telecommunications network, and

wherein the monitoring device is configured to cause the customer care action to be implemented in the telecommunications network;

train a plurality of machine learning models with the anonymized historical telecommunications data to generate a plurality of trained machine learning models;

generate accuracy scores for the plurality of trained machine learning models based on training the plurality of machine learning models;

select an optimum machine learning model, from the plurality of trained machine learning models, based on the accuracy scores for the plurality of trained machine learning models;

provide the optimum machine learning model to the monitoring device;

receive feedback associated with the monitoring device implementing the optimum machine learning model with the telecommunications network; and

perform one or more actions based on the feedback.

9. The device of claim 8 , wherein the one or more processors are further configured to:

convert, prior to training the plurality of machine learning models, the anonymized historical telecommunications data into a format compatible with training the plurality of machine learning models.

10. The device of claim 8 , wherein the one or more processors, when training the plurality of machine learning models with the anonymized historical telecommunications data, are configured to:

train the plurality of machine learning models, at a same time, with the anonymized historical telecommunications data.

11. The device of claim 8 , wherein the one or more processors, when providing the optimum machine learning model to the monitoring device, are configured to:

cause the monitoring device to implement the optimum machine learning model with the telecommunications network.

12. The device of claim 8 , wherein the optimum machine learning model causes the monitoring device to:

generate a risk score based on real time telecommunications data,

determine the customer care action for the telecommunications network based on the risk score, and

cause the customer care action to be implemented in the telecommunications network.

13. The device of claim 8 , wherein the one or more processors, when receiving the anonymized historical telecommunications data, are configured to:

periodically receive the anonymized historical telecommunications data via batch upload.

14. The device of claim 8 , wherein the one or more processors are further configured to:

receive, from the monitoring device, additional anonymized historical telecommunications data associated with the telecommunications network; and

retrain the plurality of trained machine learning models with the additional anonymized historical telecommunications data.

15. A non-transitory computer-readable medium storing a set of instructions, the set of instructions comprising:

one or more instructions that, when executed by one or more processors of a device, cause the device to:

receive, from a monitoring device, anonymized historical telecommunications data associated with a telecommunications network that is monitored with the monitoring device,

wherein the monitoring device is a separate device from the device,

wherein the monitoring device is configured to perform a set of test logins using a set of usernames and passwords,

wherein the set of usernames and passwords is anonymized to create the anonymized historical telecommunications data,

wherein the monitoring device is configured to determine a customer care action to resolve a technical issue with the telecommunications network, and

wherein the monitoring device is configured to cause the customer care action to be implemented in the telecommunications network;

train a plurality of machine learning models with the anonymized historical telecommunications data to generate a plurality of trained machine learning models;

generate accuracy scores for the plurality of trained machine learning models based on training the plurality of machine learning models;

select an optimum machine learning model, from the plurality of trained machine learning models, based on the accuracy scores for the plurality of trained machine learning models; and

provide the optimum machine learning model to the monitoring device associated with the telecommunications network to cause the monitoring device to implement the optimum machine learning model with the telecommunications network.

16. The non-transitory computer-readable medium of claim 15 , wherein the anonymized historical telecommunications data is encrypted, compressed, and anonymized to remove data identifying a telecommunications network provider and customers of the telecommunications network provider.

17. The non-transitory computer-readable medium of claim 15 , wherein the one or more instructions further cause the device to:

receive feedback associated with the monitoring device implementing the optimum machine learning model with the telecommunications network;

modify the optimum machine learning model based on the feedback and to generate a modified optimum machine learning model; and

provide the modified optimum machine learning model to the monitoring device.

18. The non-transitory computer-readable medium of claim 15 , wherein the one or more instructions further cause the device to:

convert, prior to training the plurality of machine learning models, the anonymized historical telecommunications data into a format compatible with training the plurality of machine learning models.

19. The non-transitory computer-readable medium of claim 15 , wherein the one or more instructions, that cause the device to train the plurality of machine learning models with the anonymized historical telecommunications data, cause the device to:

train the plurality of machine learning models, at a same time, with the anonymized historical telecommunications data.

20. The non-transitory computer-readable medium of claim 15 , wherein the one or more instructions further cause the device to:

receive, from the monitoring device, additional anonymized historical telecommunications data associated with the telecommunications network; and

retrain the plurality of trained machine learning models with the additional anonymized historical telecommunications data.