Artificial intelligence assisted live sports data quality assurance

1. A method comprising:

receiving, by a computing system, live event data corresponding to a live game, the live event data comprising events occurring within the live game;

analyzing, by the computing system, the live event data to identify a potential error in the live event data;

generating, by the computing system, a ticket corresponding to the potential error flagged in the live event data;

assigning, by the computing system, the ticket to a first quality assurance agent to resolve, the assigning comprising:

identifying attributes of the ticket, wherein the attributes indicate information associated with the potential error,

generating, by a first artificial intelligence model optimized for the first quality assurance agent, a first grade for the ticket based on the attributes of the ticket,

generating, by a second artificial intelligence model optimized for a second quality assurance agent, a second grade for the ticket based on the attributes of the ticket, and

determining that the first grade associated with the first quality assurance agent exceeds the second grade associated with the second quality assurance agent;

receiving, by the computing system, an indication that the ticket has been reviewed by the first quality assurance agent; and

providing, by the computing system, reviewed event data to an end user based on receiving the indication, wherein the reviewed event data is a version of the live event data.

2. The method of claim 1 , wherein assigning, by the computing system, the ticket to the first quality assurance agent to resolve, comprises:

determining that the ticket corresponds to a game that does not have any other tickets pending.

3. The method of claim 1 , further comprising:

generating, by the computing system, the first artificial intelligence model by:

identifying a plurality of historical tickets resolved by the first quality assurance agent,

for each historical ticket of the plurality of historical tickets, identifying historical attributes of the ticket and a historical grade assigned to the historical ticket by the first quality assurance agent, and

learning, by the first artificial intelligence model, to grade future tickets by correlating the historical attributes of the plurality of historical tickets with historical grades assigned to the plurality of historical tickets.

4. The method of claim 3 , further comprising:

generating, by the computing system, the second artificial intelligence model by:

identifying a second plurality of historical tickets resolved by the second quality assurance agent,

for each second historical ticket of the second plurality of historical tickets, identifying second historical attributes of the second historical ticket and a second historical grade assigned to the second historical ticket by the second quality assurance agent, and

learning, by the second artificial intelligence model, to grade the future tickets by correlating the second historical attributes of the second plurality of historical tickets with second historical grades assigned to the second plurality of historical tickets.

5. The method of claim 3 , further comprising:

retraining the first artificial intelligence model by supplementing the plurality of historical tickets graded by the first quality assurance agent with a plurality of new tickets that were graded by the first artificial intelligence model.

6. The method of claim 1 , wherein providing, by the computing system, the reviewed event data to the end user based on receiving the indication, wherein the reviewed event data is a version of the live event data comprises:

providing the reviewed event data to downstream prediction models to generate artificial intelligence insights associated with the live game.

7. The method of claim 1 , further comprising:

generating, by the computing system, a dashboard for the first quality assurance agent, wherein the dashboard indicates a number of pending tickets, a number of completed tickets, and metrics associated with the completed tickets.

8. A non-transitory computer readable medium comprising one or more sequences of instructions, which, when executed by one or more processors, causes a computing system to perform operations comprising:

receiving, by the computing system, live event data corresponding to a live game, the live event data comprising events occurring within the live game;

analyzing, by the computing system, the live event data to identify a potential error in the live event data;

generating, by the computing system, a ticket corresponding to the potential error flagged in the live event data;

assigning, by the computing system, the ticket to a first quality assurance agent to resolve, the assigning comprising:

identifying attributes of the ticket, wherein the attributes indicate information associated with the potential error,

generating, by a first artificial intelligence model optimized for the first quality assurance agent, a first grade for the ticket based on the attributes of the ticket,

generating, by a second artificial intelligence model optimized for a second quality assurance agent, a second grade for the ticket based on the attributes of the ticket, and

determining that the first grade associated with the first quality assurance agent exceeds the second grade associated with the second quality assurance agent;

receiving, by the computing system, an indication that the ticket has been reviewed by the first quality assurance agent; and

providing, by the computing system, reviewed event data to an end user based on receiving the indication, wherein the reviewed event data is a version of the live event data.

9. The non-transitory computer readable medium of claim 8 , wherein assigning, by the computing system, the ticket to the first quality assurance agent to resolve, comprises:

determining that the ticket corresponds to a game that does not have any other tickets pending.

10. The non-transitory computer readable medium of claim 8 , further comprising:

generating, by the computing system, the first artificial intelligence model by:

identifying a plurality of historical tickets resolved by the first quality assurance agent,

for each historical ticket of the plurality of historical tickets, identifying historical attributes of the ticket and a historical grade assigned to the historical ticket by the first quality assurance agent, and

learning, by the first artificial intelligence model, to grade future tickets by correlating the historical attributes of the plurality of historical tickets with historical grades assigned to the plurality of historical tickets.

11. The non-transitory computer readable medium of claim 10 , further comprising:

generating, by the computing system, the second artificial intelligence model by:

identifying a second plurality of historical tickets resolved by the second quality assurance agent,

for each second historical ticket of the second plurality of historical tickets, identifying second historical attributes of the second historical ticket and a second historical grade assigned to the second historical ticket by the second quality assurance agent, and

learning, by the second artificial intelligence model, to grade the future tickets by correlating the second historical attributes of the second plurality of historical tickets with second historical grades assigned to the second plurality of historical tickets.

12. The non-transitory computer readable medium of claim 10 , further comprising:

retraining the first artificial intelligence model by supplementing the plurality of historical tickets graded by the first quality assurance agent with a plurality of new tickets that were graded by the first artificial intelligence model.

13. The non-transitory computer readable medium of claim 8 , wherein providing, by the computing system, the reviewed event data to the end user based on receiving the indication, wherein the reviewed event data is a version of the live event data comprises:

providing the reviewed event data to downstream prediction models to generate artificial intelligence insights associated with the live game.

14. The non-transitory computer readable medium of claim 8 , further comprising:

generating, by the computing system, a dashboard for the first quality assurance agent, wherein the dashboard indicates a number of pending tickets, a number of completed tickets, and metrics associated with the completed tickets.

15. A system, comprising:

a processor; and

a memory having programming instructions stored thereon, which, when executed by the processor, causes the system to perform operations comprising:

receiving live event data corresponding to a live game, the live event data comprising events occurring within the live game;

analyzing the live event data to identify a potential error in the live event data;

generating a ticket corresponding to the potential error flagged in the live event data;

assigning the ticket to a first quality assurance agent to resolve, the assigning comprising:

identifying attributes of the ticket, wherein the attributes indicate information associated with the potential error,

generating, by a first artificial intelligence model optimized for the first quality assurance agent, a first grade for the ticket based on the attributes of the ticket,

generating, by a second artificial intelligence model optimized for a second quality assurance agent, a second grade for the ticket based on the attributes of the ticket, and

determining that the first grade associated with the first quality assurance agent exceeds the second grade associated with the second quality assurance agent;

receiving an indication that the ticket has been reviewed by the first quality assurance agent; and

providing reviewed event data to an end user based on receiving the indication, wherein the reviewed event data is a version of the live event data.

16. The system of claim 15 , wherein assigning the ticket to the first quality assurance agent to resolve, comprises:

determining that the ticket corresponds to a game that does not have any other tickets pending.

17. The system of claim 15 , wherein the operations further comprise:

generating the first artificial intelligence model by:

identifying a plurality of historical tickets resolved by the first quality assurance agent,

for each historical ticket of the plurality of historical tickets, identifying historical attributes of the ticket and a historical grade assigned to the historical ticket by the first quality assurance agent, and

learning, by the first artificial intelligence model, to grade future tickets by correlating the historical attributes of the plurality of historical tickets with historical grades assigned to the plurality of historical tickets.

18. The system of claim 17 , wherein the operations further comprise:

generating the second artificial intelligence model by:

identifying a second plurality of historical tickets resolved by the second quality assurance agent,

for each second historical ticket of the second plurality of historical tickets, identifying second historical attributes of the second historical ticket and a second historical grade assigned to the second historical ticket by the second quality assurance agent, and

learning, by the second artificial intelligence model, to grade the future tickets by correlating the second historical attributes of the second plurality of historical tickets with second historical grades assigned to the second plurality of historical tickets.

19. The system of claim 17 , wherein the operations further comprise:

retraining the first artificial intelligence model by supplementing the plurality of historical tickets graded by the first quality assurance agent with a plurality of new tickets that were graded by the first artificial intelligence model.

20. The system of claim 15 , wherein providing the reviewed event data to the end user based on receiving the indication, wherein the reviewed event data is a version of the live event data comprises:

providing the reviewed event data to downstream prediction models to generate artificial intelligence insights associated with the live game.