Collaborative system and method for validating equipment failure models in an analytics crowdsourcing environment

1. A computer implemented system for dynamically creating and validating a predictive analytics model to transform data into actionable insights, the system comprising:

an analytics server communicatively connected to: (a) a sensor configured to acquire real-time data output from an electrical system, and (b) a terminal configured to display an indicia of a set of analytics server operations; the analytics server comprising:

an event identification circuitry for identifying an event;

a tagging circuitry for selectively tagging, based on analytics expertise, at least one time series data area, where the identified event occurred;

a decision engine for comparing data area where the identified event is tagged with the data area where the identified event is not tagged;

an analytics modeling engine for building, based on analytics expertise, the predictive analytics model embodying classification generated by the selective tagging;

a terminal communicatively connected to the analytics server and configured to display the visual indicia generated by executing the predictive analytics model; and

a feedback engine for validating the predictive analytics model based on a feedback from at least one domain expert,

wherein the predictive analytics model is iteratively and collaboratively evolved based on the feedback from a community comprising two or more of a dealer community, a condition monitoring advisor community, a data scientist community, and a crowdsourcing community,

wherein the building of the predictive analytics model includes:

determining a source of a data visualization request, the source being from a dealer community member of the dealer community or a data scientist community member of the data scientist community, and

under a condition that the source of the data visualization request is from the dealer community member, creating a new created derived channel to selectively modify an algorithm corresponding to the predictive analytics model, the predictive analytics model previously having been approved via testing, wherein the dealer community member is able to change the algorithm corresponding to the predictive analytics model to meet the needs of dealer business without having to write the code for the entire predictive analytics model, and

wherein the algorithm corresponding to the predictive analytics model is written in a non-computer programming language.

2. The system of claim 1 , wherein the predictive analytics model is generated via a machine learning algorithm.

3. The system of claim 2 , wherein the collaborative evolvement of the predictive analytics model produces optimum thresholds range for the predictive analytics model based on at least one of statistical data, engineering experience, product knowledge and industry knowledge.

4. The system of claim 1 , wherein predictive analytics model becomes a ground truth once validated by the community.

5. The system of claim 1 , wherein the iterative evolvement of the predictive analytics model guards against edge cases, and produces an optimum thresholds range for at least one parameter monitored by the predictive analytics model.

6. The system of claim 1 , further comprising:

a non-data scientist interface for a non-data scientist to search for a particular asset or a group of assets to investigate at least one alert and to provide feedback for the new analytics model without having to code in a computer language; and

a data scientist user interface for a data scientist to back test the new analytics model for various use cases by verifying analytics results superimposed on machine data.

7. The system of claim 1 ,

wherein the analytics server is configured to determine whether the feedback to validate the predictive analytics model is written in a programming language or the non-programming language, and

wherein the analytics server is configured to modify a portion of code of the predictive analytics model via directly changing the code in a first case where the feedback is written in the programming language and via a user interface in a second case where the feedback is written in the non-programming language.

8. A method for dynamically creating and validating a predictive analytics model to transform data into actionable insights the method comprising:

identifying an event;

selectively tagging, based on analytics expertise, at least one time series data area, where the identified event occurred;

comparing data area where the identified event is tagged with the data area where the identified event is not tagged;

building, based on analytics expertise, the predictive analytics model embodying classification generated by said selective tagging;

displaying the visual indicia generated by executing the predictive analytics model; and

validating the predictive analytics model based on a feedback from at least one domain expert,

wherein the predictive analytics model is iteratively and collaboratively evolved based on the feedback from a community comprising two or more of a dealer community, a condition monitoring advisor community, a data scientist community, and a crowdsourcing community,

wherein said building the predictive analytics model includes:

determining a source of a data visualization request, the source being from a dealer community member of the dealer community or a data scientist community member of the data scientist community, and

under a condition that the source of the data visualization request is from the dealer community member, creating a new created derived channel to selectively modify an algorithm corresponding to the predictive analytics model, the predictive analytics model previously having been approved via testing, wherein the dealer community member can change the algorithm corresponding to the predictive analytics model to meet the needs of dealer business without having to write the code for the entire predictive analytics model, and

wherein the algorithm corresponding to the predictive analytics model is written in a non-computer programming language.

9. The method of claim 8 , wherein the predictive analytics model is generated via a machine learning algorithm.

10. The method of claim 9 , wherein the collaborative evolvement of the predictive analytics model produces optimum thresholds range for the predictive analytics model based on at least one of statistical data, engineering experience, product knowledge and industry knowledge.

11. The method of claim 8 , wherein predictive analytics model becomes a ground truth once validated by the community.

12. The method of claim 8 , wherein the iterative evolvement of the predictive analytics model guards against edge cases, and produces an optimum thresholds range for at least one parameter monitored by the predictive analytics model.

13. The method of claim 8 , further comprising:

providing a non-data scientist interface for a non-data scientist to search for a particular asset or a group of assets to investigate at least one alert and to provide feedback for the new analytics model without having to code in a computer language; and

providing a data scientist user interface for a data scientist to back test the new analytics model for various use cases by verifying analytics results superimposed on machine data.

14. The method of claim 8 , further comprising modifying a portion of code of the predictive analytics model via directly changing the code in a first case where the feedback is written in a programming language and via a user interface in a second case where the feedback is written in a non-programming language.