Systems and methods for travel optimization

1. A non-transitory computer readable medium including instructions that are executable by one or more processors to cause a system to perform a method for determining a virtual network based on a location, the method comprising:

acquiring a request for a service, wherein the request is based on a user;

acquiring a set of service providers based on the user, wherein the requested service is used to select one or more machine learning models that take preferences of the user as input to predict the set of service providers;

acquiring a first machine learning model of the one or more machine learning models, wherein the first machine learning model is based on stored information associated with other users travel patterns and with service providers providing the service, wherein the first machine learning model is trained on tradeoff optimization between popular service providers and travel distance to the popular service providers; and

generating a virtual network including a subset of service providers based on output from the first machine learning model that receives as input the set of service providers, the user's location, the user's preferences.

2. The non-transitory computer readable medium of claim 1 , wherein acquiring a first machine learning model further comprises:

building the first machine learning model based on stored information associated with the user.

3. The non-transitory computer readable medium of claim 2 , wherein building the first machine model comprises:

selecting the first machine learning model of the one or more machine learning models based on the stored information associated with the user;

training the first machine learning model based on the other users travel patterns, wherein the travel patterns include tradeoff optimization between popular service providers and travel distance to the popular service providers.

4. The non-transitory computer readable medium of claim 3 , wherein the tradeoff optimization is determined using a second machine learning model based on reinforcement learning pattern.

5. The non-transitory computer readable medium of claim 1 , wherein acquiring a first machine learning model that is based on stored information associated with other users travel patterns and with service provider providing service comprises:

determining a second set of travel patterns associated with the requested service, based on a third machine learning model built for multi-objective optimization; and

combining the second set of travel patterns with the other users travel patterns to identify related travel patterns.

6. The non-transitory computer readable medium of claim 5 , wherein the other users travel patterns further comprises:

identifying one or more other users in user's location wherein a past request for a service was associated with other user of the one or more other users.

7. The non-transitory computer readable medium of claim 6 , wherein the other users travel patterns further comprises:

identifying one or more other users accessing service providers in the user's location.

8. The non-transitory computer readable medium of claim 1 , wherein the user's location is a location provided by the user.

9. The non-transitory computer readable medium of claim 1 , wherein the user's location is associated with geographical information acquired by:

sending a request to a remote mapping service to provide geographical information; and

receiving landmarks and transportation details.

10. The non-transitory computer readable of claim 1 , wherein generating a virtual network including a subset of service providers based on output from the first machine learning model comprises:

generating using the first machine learning model one or more scores for each of the acquired set of service providers, wherein the one or more scores are based on measurement criteria; and

aggregating one or more scores of a service provider and the user preferences;

determining a rank of the service provider based on the aggregated one or more scores of the service provider; and

selecting the subset of service providers based on the rank of the service provider.

11. The non-transitory computer readable medium of claim 10 , wherein the measurement criteria includes at least one of: quality, efficiency, or conversion.

12. The non-transitory computer readable medium of claim 10 , wherein selecting the subset of service providers based on the rank of the service provider comprises:

filtering the service provider based on the other users travel patterns.

13. A method performed by a system for determining a virtual network based on a location, the method comprising:

acquiring a request for a service, wherein the request is based on a user;

acquiring a set of service providers based on the user, wherein the requested service is used to select one or more machine learning models that take preferences of the user as input to predict the set of service providers;

acquiring a first machine learning model of the one or more machine learning models, wherein the first machine learning model is based on stored information associated with other users travel patterns and with service providers providing the service, wherein the first machine learning model is trained on tradeoff optimization between popular service providers and travel distance to the popular service providers; and

generating a virtual network including a subset of service providers based on output from the first machine learning model that receives as input the set of service providers, the user's location, the user's preferences.

14. The method of claim 13 , wherein acquiring a first machine learning model further comprises:

building the first machine learning model based on stored information associated with the user.

15. The method of claim 14 , wherein building the first machine model comprises:

selecting the first machine learning model of the one or more machine learning models based on the stored information associated with the user;

training the first machine learning model based on the other users travel patterns, wherein the travel patterns include tradeoff optimization between popular service providers and travel distance to the popular service providers.

16. The method of claim 15 , wherein the tradeoff optimization is determined using a second machine learning model based on reinforcement learning pattern.

17. The method of claim 13 , wherein acquiring a first machine learning model that is based on stored information associated with other users travel patterns and with service provider providing service comprises:

determining a second set of travel patterns associated with the requested service, based on a third machine learning model built for multi-objective optimization; and

combining the second set of travel patterns with the other users travel patterns to identify related travel patterns.

18. The method of claim 17 , wherein the other users travel patterns further comprises:

identifying one or more other users in user's location wherein a past request for a service was associated with other user of the one or more other users.

19. The method of claim 13 , wherein generating a virtual network including a subset of service providers based on output from the first machine learning model comprises:

generating using the first machine learning model one or more scores for each of the acquired set of service providers, wherein the one or more scores are based on measurement criteria; and

aggregating one or more scores of a service provider and the user preferences;

determining a rank of the service provider based on the aggregated one or more scores of the service provider; and

selecting the subset of service providers based on the rank of the service provider.

20. A travel optimization system comprising:

one or more memory devices storing processor-executable instructions; and

one or more processors configured to execute the instructions to cause the travel optimization system to perform:

acquiring a request for a service, wherein the request is based on a user;

acquiring a set of service providers based on the user, wherein the requested service is used to select one or more machine learning models that take preferences of the user as input to predict the set of service providers;

acquiring a first machine learning model of the one or more machine learning models, wherein the first machine learning model is based on stored information associated with other users travel patterns and with service providers providing the service, wherein the first machine learning model is trained on tradeoff optimization between popular service providers and travel distance to the popular service providers; and

generating a virtual network including a subset of service providers based on output from the first machine learning model that receives as input the set of service providers, the user's location, the user's preferences.