Real-time convergence analysis of machine learning population output in rapid changing and adversarial environments

1. An artificial intelligence system for real-time event trend analysis using a population of machine learning models, the artificial intelligence system comprising:

a population of machine learning models clustered into a plurality of hierarchical sub-populations, the population being configured to monitor a real-time data stream; and

a controller configured for analyzing the population of machine learning models and determining data trends in response to changes in the real-time data stream, the controller comprising at least one memory device with computer-readable program code stored thereon, at least one communication device connected to a network, and at least one processing device, wherein the at least one processing device is configured to execute the computer-readable program code to:

receive a collective output from the population of machine learning models, wherein the collective output comprises an analysis of the real-time data stream;

extract an event horizon data trend based on the collective output, the event horizon data trend comprising a determined upcoming data variation in the real-time data stream, wherein extracting the event horizon data trend comprises hierarchically evaluating the collective output of at least a portion of the sub-populations; and

reconfigure, continuously, the population of machine learning models based on the collective output and the event horizon data trend.

2. The artificial intelligence system of claim 1 , wherein extracting the event horizon data trend further comprises identifying a convergent output of the population of machine learning models, wherein the convergent output comprises a majority portion of the collective output associated with a number of the population of machine learning models that are in agreement.

3. The artificial intelligence system of claim 2 , wherein the at least one processing device is further configured to execute the computer-readable program code to:

determine that the number of the population of machine learning models in agreement is above a predetermined threshold; and

in response to determining that the number of the population of the machine learning models in agreement is above the predetermined threshold, reconfigure the population of machine learning models.

4. The artificial intelligence system of claim 3 , wherein reconfiguring the population of machine learning models adjusts the number of the population of machine learning models that are in agreement.

5. The artificial intelligence system of claim 2 , wherein extracting the event horizon data trend further comprises identifying a divergent output of the population of machine learning models, wherein the divergent output comprises a minority portion of the collective output associated with another number of the population of machine learning models.

6. The artificial intelligence system of claim 5 , wherein the at least one processing device is further configured to execute the computer-readable program code to identify a vulnerability of the population of machine learning models based on at least one of the convergent output and the divergent output of the population of the machine learning models.

7. The artificial intelligence system of claim 1 , wherein reconfiguring the population of the machine learning models comprises retraining the population of machine learning models based on at least one of historical data, real-time data, adversarial data, and synthetically generated data.

8. The artificial intelligence system of claim 7 , wherein the at least one of the historical data, the real-time data, the adversarial data, and the synthetically generated data comprises misappropriation data and strategies.

9. The artificial intelligence system of claim 1 , wherein reconfiguring the population of machine learning models comprises changing architectural parameters of the population, and wherein the architectural parameters comprise at least one of adding a new model to the population, removing a current model from the population, and reweighting a current model from the population.

10. A computer-implemented method for real-time event trend analysis using a population of machine learning models, the computer-implemented method comprising:

providing a population of machine learning models clustered into a plurality of hierarchical sub-populations, the population being configured to monitor a real-time data stream; and

providing a controller configured for analyzing the population of machine learning models and determining data trends in response to changes in the real-time data stream, the controller comprising at least one memory device with computer-readable program code stored thereon, at least one communication device connected to a network, and at least one processing device, wherein the at least one processing device is configured to execute the computer-readable program code to:

receive a collective output from the population of machine learning models, wherein the collective output comprises an analysis of the real-time data stream;

extract an event horizon data trend based on the collective output, the event horizon data trend comprising a determined upcoming data variation in the real-time data stream, wherein extracting the event horizon data trend comprises hierarchically evaluating the collective output of at least a portion of the sub-populations; and

reconfigure, continuously, the population of machine learning models based on the collective output and the event horizon data trend.

11. The computer-implemented method of claim 10 , wherein extracting the event horizon data trend further comprises identifying a convergent output of the population of machine learning models, wherein the convergent output comprises a majority portion of the collective output associated with a number of the population of machine learning models that are in agreement.

12. The computer-implemented method of claim 11 , wherein the at least one processing device is further configured to execute the computer-readable program code to:

determine that the number of the population of machine learning models in agreement is above a predetermined threshold; and

in response to determining that the number of the population of the machine learning models in agreement is above the predetermined threshold, reconfigure the population of machine learning models.

13. The computer-implemented method of claim 12 , wherein reconfiguring the population of machine learning models adjusts the number of the population of machine learning models in agreement.

14. The computer-implemented method of claim 11 , wherein extracting the event horizon data trend further comprises identifying a divergent output of the population of machine learning models, wherein the divergent output comprises a minority portion of the collective output associated with another number of the population of machine learning models.

15. The computer-implemented method of claim 14 , wherein the at least one processing device is further configured to execute the computer-readable program code to identify a vulnerability of the population of machine learning models based on at least one of the convergent output and the divergent output of the population of the machine learning models.

16. The computer-implemented method of claim 10 , wherein reconfiguring the population of the machine learning models comprises retraining the population of machine learning models based on at least one of historical data, real-time data, adversarial data, and synthetically generated data.

17. The computer-implemented method of claim 10 , wherein reconfiguring the population of machine learning models comprises changing architectural parameters of the population, and wherein the architectural parameters comprise at least one of adding a new model to the population, removing a current model from the population, and reweighting a current model from the population.

18. An artificial intelligence system for real-time event trend analysis using a population of machine learning models, the artificial intelligence system comprising:

a population of machine learning models clustered into a plurality of hierarchical sub-populations, the population being configured to collectively monitor a real-time data stream; and

a controller configured for analyzing the population of machine learning models and determining data trends in response to changes in the real-time data stream, the controller comprising at least one memory device with computer-readable program code stored thereon, at least one communication device connected to a network, and at least one processing device, wherein the at least one processing device is configured to execute the computer-readable program code to:

receive a collective output from the population of machine learning models, wherein the collective output comprises an analysis of the real-time data stream;

identify a convergent output of the population of machine learning models, wherein the convergent output comprises a majority portion of the collective output associated with a number of the population of machine learning models that are in agreement;

based on the convergent output, extract an event horizon data trend based on the collective output, the event horizon data trend comprising a determined upcoming data variation in the real-time data stream; and

reconfigure, continuously, the population of machine learning models based on the convergent output and the event horizon data trend, wherein reconfiguring the population of machine learning models comprises retraining and reconfiguring an architecture of the population of machine learning models.

19. The artificial intelligence system of claim of claim 18 , wherein:

extracting the event horizon data trend further comprises identifying a convergent output of the population of machine learning models, wherein the convergent output comprises a majority portion of the collective output associated with a number of the population of machine learning models that are in agreement; and

the at least one processing device is further configured to execute the computer-readable program code to:

determine that the number of the population of machine learning models in agreement is above a predetermined threshold; and

in response to determining that the number of the population of the machine learning models in agreement is above the predetermined threshold, reconfigure the population of machine learning models.

20. The artificial intelligence system of claim of claim 19 , wherein extracting the event horizon data trend further comprises identifying a divergent output of the population of machine learning models, wherein the divergent output comprises a minority portion of the collective output associated with another number of the population of machine learning models.