System, method, and platform for generating a real-time bet win probability

1. A method for generating a win probability, the method comprising:

receiving, at a computer system, a first data set, wherein the first data set comprises a wager from a user on sports event;

receiving, at the computer system, a second data set, wherein the second data set comprises game data of the sports event;

combining, via at least one processor of the computer system, the first data set with the second data set, resulting in a combined data set;

training, via the at least one processor executing a machine learning training algorithm using a historical data set, a win probability model, wherein the historical data set comprises:

historical game data associated with at least one historical game; and

historical wager data associated with the at least one historical game;

iteratively executing, via the at least one processor, the win probability model, wherein inputs to the win probability model comprise the combined data set, resulting in a win probability of the wager;

tuning the win probability model based on at least one of live observation and historical trends; and

displaying the win probability to the user.

2. The method of claim 1 , wherein the game data of the sports event comprises real-time game data of an ongoing sports event.

3. The method of claim 1 , further comprising:

updating the second data set using updated game data, resulting in an updated second data set; and

re-executing, via the at least one processor, the win probability model using the updated win probability based on the updated second data set.

4. The method of claim 3 , wherein the second data set is updated in real-time during the sports event.

5. The method of claim 3 , wherein the second data set is updated at a predetermined time interval.

6. The method of claim 3 , further comprising:

determining a predetermined event has occurred in the sports event based on the updated second data set; and

wherein the re-executing of the win probability model occurs after determining the predetermined event has occurred.

7. The method of claim 1 , wherein the win probability model is generated using an algorithm, the algorithm comprising at least one of a supervised machine-learning algorithm, a linear regression algorithm, a k-nearest neighbors algorithm, a decision tree algorithm, and a neural network.

8. The method of claim 7 , wherein the algorithm correlates a game characteristic and a wager outcome.

9. A non-transitory computer readable medium having stored thereon software instructions that, when executed by a processor, cause the processor to generate a win probability of a wager, by executing the steps comprising:

receiving a first data set, wherein the first data set comprises a wager from a user on sports event;

receiving a second data set, wherein the second data set comprises game data of the sports event;

combining the first data set with the second data set, resulting in a combined data set;

training, by executing a machine learning training algorithm using a historical data set, a win probability model, wherein the historical data set comprises:

historical game data associated with at least one historical game; and

historical wager data associated with the at least one historical game;

iteratively executing the win probability model, wherein inputs to the win probability model comprise the combined data set, resulting in a win probability of the wager;

tuning the win probability model based on at least one of live observation and historical trends; and

displaying the win probability to the user.

10. The non-transitory computer readable medium of claim 9 , wherein the game data of the sports event comprises real-time game data of an ongoing sports event.

11. The non-transitory computer readable medium of claim 9 , further comprising:

updating the second data set using updated game data, resulting in an updated second data set; and

re-executing, via the at least one processor, the win probability model using the updated win probability based on the updated second data set.

12. The non-transitory computer readable medium of claim 11 , wherein the second data set is updated in real-time during the sports event.

13. The non-transitory computer readable medium of claim 11 , wherein the second data set is updated at a predetermined time interval.

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

determining a predetermined event has occurred in the sports event based on the updated second data set; and

wherein the re-executing of the win probability model occurs after determining the predetermined event has occurred.

15. The non-transitory computer readable medium of claim 9 , wherein the win probability model is generated using an algorithm, the algorithm comprising at least one of a supervised machine-learning algorithm, a linear regression algorithm, a k-nearest neighbors algorithm, a decision tree algorithm, and a neural network.

16. The non-transitory computer readable medium of claim 15 , wherein the win probability model correlates a game characteristic and a wager outcome.

17. The method of claim 1 , further comprising:

receiving, at the computer system after the generation of the win probability, updated historical data;

comparing, via the at least one processor, the win probability to the updated historical data, resulting in a comparison; and

retraining, via the at least one processor executing the machine learning training algorithm using the historical data set and the updated historical data, the win probability model.

18. The non-transitory computer readable medium of claim 9 , having additional instructions stored which, when executed by the processor, cause the processor to perform operations comprising:

receiving, after the generation of the win probability, updated historical data;

comparing the win probability to the updated historical data, resulting in a comparison; and

retraining, by executing the machine learning training algorithm using the historical data set and the updated historical data, the win probability model.