Determining the health of an IOT application

1. A computing device comprising:

a storage configured to store an expected predictive output of an Internet of Things (IoT) analytic application deployed on a cloud platform;

a processor configured to receive an actual predictive output of the IoT analytic application running on a host platform, select at least one performance metric, from among a plurality of performance metrics, based on a type of the IoT analytic application, determine a predictive accuracy performance value that identifies how accurate the IoT analytic application is at making predictions in association with an industrial asset based on the selected at least one performance metric, the actual predictive output of the IoT analytic application, and the expected predictive output of the IoT analytic application, and determine that a predictive performance of the IoT analytic application running on the host platform has deteriorated based on the determined predictive accuracy performance value,

wherein the processor is configured to dynamically provide the at least one performance metric based on the type of the IoT application including:

at least one of a receiver operating characteristic (ROC) curve, a confusion matrix, and a lift chart, in response to the type of the IoT analytic application being a classification based IoT analytic,

at least one of R squared, mean absolute error (MAE), mean squared error (MSE), and mean square root error (RMSE), in response to the type of the IoT analytic application being a regression based IoT analytic, or

at least one of MAE, MSE, a plot of MAE against a plot of forecast time horizon, and a confidence interval plot, in response to the type of the IoT analytic application being a time-series based IoT analytic, and

the processor is further configured to transmit an alert to a user device indicating that the predictive performance of the IoT analytic application running on the host platform has deteriorated.

2. The computing device of claim 1 , wherein the predictive accuracy performance value identifies how successful the IoT analytic application is at making predications in association with an industrial asset based on a comparison of the received actual predictive output of the IoT analytic application and the expected predictive output of the IoT analytic application using the selected at least one performance metric.

3. The computing device of claim 1 , wherein the processor is further configured to display, via a user interface, a list of performance metrics associated with the IoT analytic application that are capable of being selected by a user.

4. The computing device of claim 1 , wherein the processor is configured to display the list of performance metrics including at least one of the ROC curve, the confusion matrix, and the lift chart, in response to the type of the IoT analytic application being the classification based IoT analytic.

5. The computing device of claim 1 , wherein the processor is configured to display the list of performance metrics including at least one of the R squared, the MAE, the MSE, and the RMSE, in response to the type of the IoT analytic application being the regression based IoT analytic.

6. The computing device of claim 1 , wherein the processor is configured to display the list of performance metrics including at least one of the MAE, the MSE, the plot of MAE against the plot of forecast time horizon, and the confidence interval plot, in response to the type of the IoT analytic application being the time-series based IoT analytic.

7. The computing device of claim 1 , wherein the processor is further configured to receive a new predictive output of the IoT analytic application deployed on the cloud platform, and determine another predictive accuracy performance value of the IoT analytic application based on the previously selected at least one performance metric, the newly received predictive output of the IoT analytic application, and the expected predictive output of the IoT analytic application.

8. A method comprising:

receiving an actual predictive output of an IoT analytic application deployed on a host platform;

selecting at least one performance metric, from among a plurality of performance metrics, based on a type of the IoT analytic application;

determine a predictive accuracy performance value that identifies how accurate the IoT analytic application is at making predictions in association with an industrial asset based on the selected at least one performance metric, the received actual predictive output of the IoT analytic application on the host platform, and an expected predictive output of the IoT analytic application;

determining that a predictive performance of the IoT analytic application on the host platform has deteriorated based on the determined predictive accuracy performance value;

dynamically providing the at least one performance metric based on the type of the IoT application including:

at least one of a receiver operating characteristic (ROC) curve, a confusion matrix, and a lift chart, in response to the type of the IoT analytic application being a classification based IoT analytic,

at least one of R squared, mean absolute error (MAE), mean squared error (MSE), and mean square root error (RMSE), in response to the type of the IoT analytic application being a regression based IoT analytic, or

at least one of MAE, MSE, a plot of MAE against a plot of forecast time horizon, and a confidence interval plot, in response to the type of the IoT analytic application being a time-series based IoT analytic, and

in response, transmitting an alert to a user device indicating that the predictive performance of the IoT analytic application deployed on the host platform has deteriorated.

9. The method of claim 8 , wherein the predictive accuracy performance value identifies how successful the IoT analytic application is at making predictions in association with an industrial asset based on a comparison of the received predictive output of the IoT analytic application and the expected predictive output of the IoT analytic application using the selected at least one performance metric.

10. The method of claim 8 , further comprising displaying, via a user interface, a list of performance metrics associated with the IoT analytic application that are capable of being selected by a user.

11. The method of 10 , wherein the displayed list of performance metrics comprises at least one of the ROC curve, the confusion matrix, and the lift chart, in response to the type of the IoT analytic application being the classification based IoT analytic.

12. The method of claim 10 , wherein the displayed list comprises of performance metrics comprises at least one of the R squared, the MAE, the MSE, and the RMSE, in response to the type of the IoT analytic application being the regression based IoT analytic.

13. The method of claim 10 , wherein the displayed list of performance metrics comprises at least one of MAE, MSE, a plot of MAE against a plot of forecast time horizon, and a confidence interval plot, in response to the type of the IoT analytic application being a time-series based IoT analytic.

14. The method of claim 8 , further comprising receiving a new predictive output of the IoT analytic application deployed on the cloud platform, and

determining another predictive performance value of the IoT analytic application based on the previously selected at least one performance metric, the newly received predictive output of the IoT analytic application, and the expected predictive output of the IoT analytic application.

15. A non-transitory computer readable medium having stored therein instructions that when executed cause a computer to perform a method for monitoring a health of an Internet of Things (IoT) application, the method comprising:

receiving an actual predictive output of an IoT analytic application deployed on a host platform;

selecting at least one performance metric, from among a plurality of performance metrics, based on a type of the IoT analytic application;

determining a predictive accuracy performance value that identifies how accurate the IoT analytic application is at making predictions in association with an industrial asset based on the selected at least one performance metric, the received actual predictive output of the IoT analytic application on the host platform, and an expected predictive output of the IoT analytic application;

determining that a predictive performance of the IoT analytic application on the host platform has deteriorated based on the determined predictive accuracy performance value;

dynamically providing the at least one performance metric based on the type of the IoT application including:

at least one of a receiver operating characteristic (ROC) curve, a confusion matrix, and a lift chart, in response to the type of the IoT analytic application being a classification based IoT analytic,

at least one of R squared, mean absolute error (MAE), mean squared error (MSE), and mean square root error (RMSE), in response to the type of the IoT analytic application being a regression based IoT analytic, or

at least one of MAE, MSE, a plot of MAE against a plot of forecast time horizon, and a confidence interval plot, in response to the type of the IoT analytic application being a time-series based IoT analytic, and

in response, transmitting an alert to a user device indicating that the predictive performance of the IoT analytic application deployed on the host platform has deteriorated.

16. The non-transitory computer readable medium of claim 15 , wherein the predictive accuracy performance value identifies how successful the IoT analytic application is at making predictions in association with an industrial asset based on a comparison of the received actual predictive output of the IoT analytic application and the expected predictive output of the IoT analytic application using the selected performance metrics.

17. The non-transitory computer readable medium of claim 15 , wherein the method further comprises displaying, via a user interface, a list of performance metrics associated with the IoT analytic application that are capable of being selected by a user.