Assisted analytics

1. A computer-implemented method of assisted analytics, comprising:

responsive to a user selection of a measure that is calculated from a data set that is characterized by a plurality of dimensions of data, populating, with a processor a set of dimensions of the data with dimensions that contribute at least one data value to the user selected measure, wherein the set of dimensions comprises a subset of the plurality of dimensions of data;

automatically detecting with the processor, a difference between the user selected measure and at least one normalized measure of a same type as the user selected measure;

calculating with the processor and based at least in part on the detected difference, for each dimension of the data in the set of dimensions of data a measure outlier threshold for a set of timeframe-specific values of the user selected measure;

calculating with the processor, for each dimension of the data in the set of dimensions of data a dimension-specific outlier factor by aggregating timeframe-specific outlier weights for each timeframe in which a timeframe-specific value in the set of timeframe-specific values exceeds the measure outlier threshold;

presenting in an electronic interface, the dimensions in the set of dimensions of data in a ranked order that is based on the dimension-specific outlier factor; and

determining an operation improvement based on the ranked order.

2. The computer-implemented method of claim 1 , wherein the ranked order is limited to dimensions for which an outlier is determined.

3. The computer-implemented method of claim 1 , wherein the timeframe-specific outlier weights are calculated based on a relationship of each specific timeframe to an assisted analytics reference timeframe.

4. The computer-implemented method of claim 1 , wherein the timeframe-specific outlier weights are calculated based on a relationship of each specific timeframe to a cycle timeframe.

5. The computer-implemented method of claim 1 , wherein determining a measure outlier threshold comprises calculating p-values based on statistical tests of the set of timeframe-specific values of the measure.

6. The computer-implemented method of claim 1 , wherein determining a measure outlier threshold comprises applying control charts to the set of timeframe-specific values of the measure to derive an indicator of an outlier trend of the set of timeframe-specific values of the measure.

7. The computer-implemented method of claim 1 , wherein determining a measure outlier threshold comprises generating at least one of an average and a standard deviation of the set of timeframe-specific values of the measure.

8. The computer-implemented method of claim 1 , wherein the user selected measure is calculated from data in the data set for a plurality of timeframes that is independent of the specific timeframes for which outliers of the user selected measure are determined.

9. The computer-implemented method of claim 1 , wherein the set of timeframe-specific values of the measure correspond to a plurality of sequential timeframes for which the measure was calculated.

10. The computer-implemented method of claim 1 , wherein the set of timeframe-specific values of the measure correspond to measures calculated for each month in a set of recent twelve months.

11. The computer-implemented method of claim 1 , wherein a set of timeframes from which the set of timeframe-specific values is derived is automatically determined based on timeframe-related attributes of the data set.

12. The computer-implemented method of claim 1 , wherein calculating a dimension outlier threshold comprises adjusting an existing value of the dimension outlier threshold based on a count of values that exceed the dimension outlier threshold so that the count of values that exceed the adjusted dimension outlier threshold is reduced.

13. A computer-implemented method of assisted analytics, comprising:

responsive to a user selection of a measure that is calculated from a data set that is characterized by a plurality of dimensions of data, populating, with a processor a set of dimensions of the data with dimensions that contribute at least one data value to the selected measure, wherein the set of dimensions comprises a subset of the plurality of dimensions of data;

calculating with the processor, for each dimension of the data in the set of dimensions of the data a set of timeframe-specific values of a plurality of measures of data specific to each dimension;

automatically detecting with the processor, for each of the measures of the plurality of measures, a corresponding difference between the measure and at least one normalized measure of a same type as the measure;

calculating with the processor, for each of the measures of the plurality of measures, a measure outlier threshold based at least in part on the difference corresponding to the measure;

calculating with the processor, for each dimension of the data in the set of dimensions of data a dimension-specific outlier factor by aggregating timeframe-specific outlier weights for each timeframe in which a timeframe-specific value in the set of timeframe-specific values exceeds the measure outlier threshold; and

presenting in an electronic interface, the dimensions in the set of dimensions of data in a ranked order that is based on the dimension-specific outlier factor;

wherein calculating a measure outlier threshold comprises applying control charts to the set of timeframe-specific values of the measure to derive an indicator of an outlier trend of the set of timeframe-specific values of the measure.

14. The computer-implemented method of claim 13 , wherein determining a measure outlier threshold comprises calculating p-values based on statistical tests of the set of timeframe-specific values of the measure.

15. An assisted analytics system comprising:

a user interface of a computing system through which a user is enabled to select a measure of data in a data set that is characterized by a plurality of dimensions of data;

a digital data set comprising dimensions of the data that is populated with dimensions that contribute at least one data value to the selected measure responsive to the selection of a measure in the user interface, wherein the digital data set comprises a subset of the plurality of the dimensions of data;

a measure differentiation circuit structured to automatically detect a difference between the user selected measure and at least one normalized measure of a same type as the user selected measure;

a measure outlier threshold calculation circuit that calculates, based at least in part on the detected difference, for each dimension of the data in the digital data set, a measure outlier threshold for a set of timeframe-specific values of the user selected measure;

a dimension-specific outlier factor calculation circuit that calculates, for each dimension of the data in the digital data set, a dimension-specific outlier factor by aggregating timeframe-specific outlier weights for each timeframe in which a timeframe-specific value in the set of timeframe-specific values exceeds the measure outlier threshold;

an electronic interface in which the dimensions in the digital data set are presented in a ranked order that is based on the dimension-specific outlier factor; and

an operation determination circuit that determines an operation improvement based on the ranked order.

16. The assisted analytics system of claim 15 , wherein the ranked order of dimensions in the digital data set is limited to dimensions for which an outlier is determined.

17. The assisted analytics system of claim 15 , wherein the user selected measure is derived from data in the digital data set for a plurality of timeframes that are independent of the specific timeframes for which outliers of the selected measure are determined.

18. A computer-implemented method of assisted analytics, comprising:

responsive to a user selection of a measure that is calculated from a data set that is characterized by a plurality of dimensions of data, populating, with a processor a set of dimensions of the data with dimensions that contribute at least one data value to the user selected measure, wherein the set of dimensions comprises a subset of the plurality of dimensions of data;

automatically detecting with the processor, a difference between the user selected measure and at least one normalized measure of a same type as the user selected measure;

calculating with the processor and based at least in part on the detected difference, for each dimension of the data in the set of dimensions of data a measure outlier threshold for a set of timeframe-specific values of the user selected measure;

calculating with the processor, for each dimension of the data in the set of dimensions of data a dimension-specific outlier factor by aggregating timeframe-specific outlier weights for each timeframe in which a timeframe-specific value in the set of timeframe-specific values exceeds the measure outlier threshold; and

presenting in an electronic interface, the dimensions in the set of dimensions of data in a ranked order that is based on the dimension-specific outlier factor;

wherein determining a measure outlier threshold comprises applying control charts to the set of timeframe-specific values of the measure to derive an indicator of an outlier trend of the set of timeframe-specific values of the measure.

19. The computer-implemented method of claim 18 , wherein the ranked order is limited to dimensions for which an outlier is determined.

20. The computer-implemented method of claim 18 , wherein the timeframe-specific outlier weights are calculated based on a relationship of each specific timeframe to an assisted analytics reference timeframe.

21. The computer-implemented method of claim 18 , wherein the timeframe-specific outlier weights are calculated based on a relationship of each specific timeframe to a cycle timeframe.

22. The computer-implemented method of claim 18 , wherein determining a measure outlier threshold comprises calculating p-values based on statistical tests of the set of timeframe-specific values of the measure.

23. The computer-implemented method of claim 18 , wherein determining a measure outlier threshold comprises generating at least one of an average and a standard deviation of the set of timeframe-specific values of the measure.

24. A computer-implemented method of assisted analytics, comprising:

responsive to a user selection of a measure that is calculated from a data set that is characterized by a plurality of dimensions of data, populating, with a processor a set of dimensions of the data with dimensions that contribute at least one data value to the user selected measure, wherein the set of dimensions comprises a subset of the plurality of dimensions of data;

automatically detecting with the processor, a difference between the user selected measure and at least one normalized measure of a same type as the user selected measure;

calculating with the processor and based at least in part on the detected difference, for each dimension of the data in the set of dimensions of data a measure outlier threshold for a set of timeframe-specific values of the user selected measure;

calculating with the processor, for each dimension of the data in the set of dimensions of data a dimension-specific outlier factor by aggregating timeframe-specific outlier weights for each timeframe in which a timeframe-specific value in the set of timeframe-specific values exceeds the measure outlier threshold; and

presenting in an electronic interface, the dimensions in the set of dimensions of data in a ranked order that is based on the dimension-specific outlier factor;

wherein calculating a dimension outlier threshold comprises adjusting an existing value of the dimension outlier threshold based on a count of values that exceed the dimension outlier threshold so that the count of values that exceed the adjusted dimension outlier threshold is reduced.

25. The computer-implemented method of claim 24 , wherein the ranked order is limited to dimensions for which an outlier is determined.

26. The computer-implemented method of claim 24 , wherein the timeframe-specific outlier weights are calculated based on a relationship of each specific timeframe to an assisted analytics reference timeframe.

27. The computer-implemented method of claim 24 , wherein the timeframe-specific outlier weights are calculated based on a relationship of each specific timeframe to a cycle timeframe.

28. The computer-implemented method of claim 24 , wherein determining a measure outlier threshold comprises calculating p-values based on statistical tests of the set of timeframe-specific values of the measure.

29. The computer-implemented method of claim 24 , wherein determining a measure outlier threshold comprises applying control charts to the set of timeframe-specific values of the measure to derive an indicator of an outlier trend of the set of timeframe-specific values of the measure.

30. The computer-implemented method of claim 24 , wherein determining a measure outlier threshold comprises generating at least one of an average and a standard deviation of the set of timeframe-specific values of the measure.