Data quality-based computations for KPIs derived from time-series data

1. A computer system comprising:

one or more processing devices and at least one memory device operably coupled to the one or more processing devices, the one or more processing devices are configured to:

determine one or more predicted replacement values for one or more potentially erroneous data instances in a time series data stream;

resolve the one or more potentially erroneous data instances with one predicted replacement value of the one or more predicted replacement values in the time series data stream; and

generate a plurality of simulation snapshots through point-based simulations comprising:

generate a plurality of inferred data points from the one or more potentially erroneous data instances comprising alternately assigning one of a discrete correct label and a discrete erroneous label to each potentially erroneous data instance of the one or more potentially erroneous data instances.

2. The system of claim 1 , wherein the one or more processing devices are further configured to:

identify the one or more potentially erroneous data instances in the time series data stream; and

identify one or more key performance indicators (KPIs) impacted through the one or more potentially erroneous data instances.

3. The system of claim 2 , wherein the one or more processing devices are further configured to:

determine one or more KPI formulation characteristics are associated with the one or more potentially erroneous data instances, wherein each KPI of the one or more KPIs includes one or more formulations thereof, each formulation of the one or more formulations includes one or more characteristics thereof.

4. The system of claim 3 , wherein the one or more processing devices are further configured to:

analyze KPI formulations that are observable, thereby analyzing observable box formulations; and

analyze KPI formulations that are non-observable, thereby analyzing unobservable box formulations.

5. The system of claim 3 , wherein the one or more processing devices are further configured to:

generate one or more simulation snapshots, wherein each simulation snapshot of the one or more simulation snapshots includes one or more imputed values, wherein each predicted replacement value of the one or more predicted replacement values is at least partially based on the one or more imputed values and the one or more KPI formulation characteristics.

6. The system of claim 5 , wherein the one or more processing devices are further configured to:

generate the plurality of simulation snapshots through point-based simulations further comprising:

generate a set of all possible combinations of the plurality of inferred data points;

determine probabilities of the plurality of inferred data points actually being erroneous; and

generate the plurality of point-based simulation snapshots on only a subset of the set of all possible combinations of the plurality of inferred data points, wherein each point-based simulation snapshot of the plurality of point-based simulation snapshots includes the one or more imputed values; and

generate a plurality of simulation snapshots through method-based simulations comprising:

generate the one or more imputed values for each potentially erroneous data instance, wherein each imputed value of the one or more imputed values is generated through a respective remediation operation.

7. The system of claim 6 , wherein the one or more processing devices are further configured to:

generate the subset of the set of all possible combinations of the plurality of inferred data points comprising employment of snapshot optimization features through using the KPI formulation characteristics.

8. The system of claim 1 , wherein the one or more processing devices are further configured to:

determine a confidence value for each predicted replacement value of the one or more predicted replacement values in the time series data stream;

generate an explanatory basis for the resolution of the one or more potentially erroneous data instances in the time series data stream; and

resolve the one or more potentially erroneous data instances and generate the explanatory basis for the resolution of the one or more potentially erroneous data instances through one or more of quantity-based confidence measures and spread-based confidence measures.

9. A computer program product, comprising:

one or more computer readable storage media;

program instructions collectively stored on the one or more computer storage media, the program instructions comprising:

program instructions to determine one or more predicted replacement values for one or more potentially erroneous data instances in a time series data stream; and

program instructions to resolve the one or more potentially erroneous data instances with one predicted replacement value of the one or more predicted replacement values in the time series data stream; and

program instructions to generate a plurality of simulation snapshots through point-based simulations comprising:

program instructions to generate a plurality of inferred data points from the one or more potentially erroneous data instances comprising alternately assigning one of a discrete correct label and a discrete erroneous label to each potentially erroneous data instance of the one or more potentially erroneous data instances.

10. The computer program product of claim 9 , further comprising:

program instructions to identify the one or more potentially erroneous data instances in the time series data stream; and

program instructions to identify one or more key performance indicators (KPIs) impacted through the one or more potentially erroneous data instances.

11. The computer program product of claim 10 , further comprising:

program instructions to determine one or more of KPI formulation characteristics are associated with the one or more potentially erroneous data instances, wherein each KPI of the one or more KPIs includes one or more formulations thereof, each formulation of the one or more formulations includes one or more characteristics thereof.

12. The computer program product of claim 11 , further comprising:

program instructions to generate one or more simulation snapshots, wherein each simulation snapshot of the one or more simulation snapshots includes the one or more imputed values, wherein each predicted replacement value of the one or more predicted replacement values is at least partially based on the one or more imputed values and the one or more KPI formulation characteristics.

13. A computer-implemented method comprising:

determining one or more predicted replacement values for one or more potentially erroneous data instances in a time series data stream;

resolving the one or more potentially erroneous data instances with one predicted value of the one or more predicted values in the time series data stream; and

generating a plurality of simulation snapshots through point-based simulations comprising:

generating a plurality of inferred data points from the one or more potentially erroneous data instances comprising alternately assigning one of a discrete correct label and a discrete erroneous label to each potentially erroneous data instance of the one or more potentially erroneous data instances.

14. The method of claim 13 , further comprising:

identifying the one or more potentially erroneous data instances in the time series data stream; and

identifying one or more key performance indicators (KPIs) impacted through the one or more potentially erroneous data instances.

15. The method of claim 14 , wherein each KPI of the one or more KPIs includes one or more formulations thereof, each formulation of the one or more formulations includes one or more characteristics thereof, the method further comprising:

determining one or more of the KPI formulation characteristics are associated with the one or more potentially erroneous data instances.

16. The method of claim 15 , wherein determining the one or more KPI formulation characteristics comprises:

analyzing KPI formulations that are observable, thereby analyzing observable box formulations; and

analyzing KPI formulations that are non-observable, thereby analyzing unobservable box formulations.

17. The method of claim 15 , wherein determining the one or more predicted replacement values comprises:

generating one or more simulation snapshots, wherein each simulation snapshot of the one or more simulation snapshots includes the one or more imputed values, wherein each predicted replacement value of the one or more predicted replacement values is at least partially based on the one or more imputed values and the one or more KPI formulation characteristics.

18. The method of claim 17 , further comprising one or more of:

the generating the plurality of simulation snapshots through point-based simulations further comprising:

generating a set of all possible combinations of the plurality of inferred data points;

determining probabilities of the plurality of inferred data points actually being erroneous; and

generating the plurality of point-based simulation snapshots on only a subset of the set of all possible combinations of the plurality of inferred data points, wherein each point-based simulation snapshot of the plurality of point-based simulation snapshots includes the one or more imputed values; and

generating a plurality of simulation snapshots through method-based simulations comprising:

generating the one or more imputed values for each potentially erroneous data instance, wherein each imputed value of the one or more imputed values is generated through a respective remediation operation.

19. The method of claim 18 , further comprising:

generating the subset of the set of all possible combinations of the plurality of inferred data points comprising employing snapshot optimization features through using the KPI formulation characteristics.

20. The method of claim 13 , further comprising:

determining a confidence value for each predicted replacement value of the one or more predicted replacement values in the time series data stream;

generating an explanatory basis for the resolution of the one or more potentially erroneous data instances in the time series data stream; and

using one or more of quantity-based confidence measures and spread-based confidence measures.