Systems and methods for business analytics management and modeling

1. A computerized method for generating a model, useful in association with a business analytics system, the method comprising:

selecting a plurality of indicators relevant to a model;

generating a strength score for each of the plurality of indicators using a processor that calculates a R-squared value and procyclic values for each indicator to derive the strength scores by adding the R-squared value and procyclic values and multiplying the results by a seasonality determination, a normalized fraction of a number of model indicators over a total number of models, a normalized difference in a last update, a normalized difference between a minor outlier count and a major outlier count, and a fraction of data overlap over a frequency value of the indicator;

ranking the plurality of indicators by their strength score;

bucketizing the plurality of ranked indicators;

configuring a plurality of models using machine learning;

modeling various permutations of the bucketized indicators in parallel to generate a plurality of model forecasts;

selecting one of the plurality of model forecasts with the highest accuracy; and

generating a report using the selected one model forecast.

2. The method of claim 1 , wherein the strength score is calculated by:

(R-squared calculation+procyclic calculation)×(the seasonality determination)×((the number of models the indicator is included/the total number of models)+1)×(1−((Difference in the last updated−2)/20)))×(1−(minor outlier count/100)−(major outlier count/20))×(data overlap/frequency value of the indicator)×100,

wherein the seasonality determination is 0.95 for a seasonality indicator and 1.05 for a non-seasonality indicator, and wherein the frequency value of the indicator is 54 for monthly, 18 for quarterly, 9 for semiannually, and 5 for annually.

3. The method of claim 1 , wherein the bucketizing includes dividing the total number of data points available for the model by five and multiplying by four buckets to generate a total number of data sets.

4. The method of claim 3 , wherein the total number of data sets are divided evenly into a macroeconomic bucket, a target industry bucket, a demand industry bucket and a miscellaneous bucket.

5. The method of claim 4 , wherein the data sets in the macroeconomic bucket are national level, and the datasets in the target industry bucket, the demand industry bucket and the miscellaneous bucket are equal parts national level and local level datasets, when appropriate.

6. The method of claim 5 , wherein higher level datasets are substituted when local level datasets are unavailable.

7. The method of claim 4 , wherein the datasets are divided into the four buckets by tag information and the strength scores.

8. The method of claim 1 , wherein the report generating includes backtesting the model.

9. The method of claim 1 , wherein report generating includes calculating a single period error rate and an aggregate period error for the model.

10. The system of claim 1 , wherein report generating includes calculating a single period error rate and an aggregate period error for the model.

11. A computerized system for generating a model comprising:

a data aggregation server for selecting a plurality of indicators relevant to a model;

a data analyzer for generating a strength score for each of the plurality of indicators using a processor that calculates a R-squared value and procyclic values for each indicator to derive the strength scores by adding the R-squared value and procyclic values and multiplying the results by a seasonality determination, a normalized fraction of a number of model indicators over a total number of models, a normalized difference in a last update, a normalized difference between a minor outlier count and a major outlier count, and a fraction of data overlap over a frequency value of the indicator;

a modeling engine for configuring a plurality of models using machine learning, modeling various permutations of the bucketized indicators in parallel to generate a plurality of model forecasts, and selecting one of the plurality of model forecasts with the highest accuracy; and

a reporting module for generating a report using the selected one model forecast.

12. The system of claim 11 , wherein the strength score is calculated by:

(R-squared calculation+procyclic calculation)×(the seasonality determination)×((the number of models the indicator is included/the total number of models)+1)×(1−((difference in last updated−2)/20))×(1−(minor outlier count/100)−(major outlier count/20))×(data overlap/frequency value of the indicator)×100,

wherein the seasonality determination is 0.95 for a seasonality indicator and 1.05 for a non-seasonality indicator, and wherein the frequency value of the indicator is 54 for monthly, 18 for quarterly, 9 for semiannually, and 5 for annually.

13. The system of claim 11 , wherein the bucketizing includes dividing the total number of data points available for the model by five and multiplying by four buckets to generate a total number of data sets.

14. The system of claim 13 , wherein the total number of data sets are divided evenly into a macroeconomic bucket, a target industry bucket, a demand industry bucket and a miscellaneous bucket.

15. The system of claim 14 , wherein the data sets in the macroeconomic bucket are national level, and the datasets in the target industry bucket, the demand industry bucket and the miscellaneous bucket are equal parts national level and local level datasets, when appropriate.

16. The system of claim 15 , wherein higher level datasets are substituted when local level datasets are unavailable.

17. The system of claim 14 , wherein the datasets are divided into the four buckets by tag information and the strength scores.

18. The system of claim 11 , wherein the report generating includes backtesting the model.