Anonymous ranking service

1. A method for generating a verifiable output that represents a user's data, the method comprising:

receiving verifiable claims from a user at a recommendation service, wherein the verifiable claims are signed in accordance with a distributed identity system by issuers of the verifiable claims and wherein the verifiable claims are generated by the distributed identify system in response to a request from the user;

perform profile matching to convert the verifiable claims into a full featured vector by the recommendation service;

generating the verifiable output from the full featured vector, by the recommendation service, by augmenting private data of the user in the verifiable claims with data from other users;

providing the verifiable output to the user, wherein the verifiable output generated by the recommendation service is decoupled from the service provider;

providing the verifiable output to a service provider, wherein the service provider provides personalized services to the user using the verifiable output, wherein the verifiable output only includes the private information of the user chosen to be shared by the user.

2. The method of claim 1 , wherein the other data is obtained from collaborative filtering, statistical analysis, or input and output data associated with other users.

3. The method of claim 1 , wherein the verifiable claims are signed by an issuer.

4. The method of claim 1 , further comprising accessing a dictionary to perform the profile matching.

5. The method of claim 1 , further comprising generalizing the user's data from the verifiable claims when adding to the full featured vector.

6. The method of claim 1 , wherein the verifiable output comprises a score, a classification, of the full featured vector.

7. The method of claim 1 , further comprising sending the verifiable output to the user or to a service provider, wherein the verifiable output is signed with a decentralized identity system identifier.

8. The method of claim 1 , further comprising sending the verifiable output to the service provider, wherein the service provider personalizes a service in accordance with the verifiable output.

9. The method of claim 1 , further comprising receiving feedback from a service provider that personalized a service using the verifiable output, wherein the feedback is incorporated into the generation of subsequent verifiable outputs.

10. The method of claim 1 , wherein the distributed identity system comprises a blockchain implemented distributed identify system.

11. The method of claim 1 , further comprising including classifications or scores in the verifiable output.

12. A method for personalizing services for a client, the method comprising:

receiving, at a service provider, a verifiable output generated by a recommendation service, wherein the verifiable output is signed using a private key in accordance with a decentralized identity system, wherein generation of the verifiable output performed by the recommendation service is decoupled from the service provider, wherein the recommendation service augments private data of a user with data from other users when generating the verifiable output such that user data included in the verifiable output includes the private data of a user and the data from the other others;

identifying the user data included in the verifiable output by requesting a public key from the decentralized identity system and decrypting the verifiable output; and

personalizing a service provided by the service provider based on the user data included in the verifiable output, wherein the private information of the user is chosen to be shared by the user.

13. The method of claim 12 , further comprising receiving the verifiable output from the recommendation service via the client.

14. The method of claim 12 , wherein the verifiable output is configured specifically fora business use of the service provider.

15. The method of claim 12 , wherein the verifiable output includes one or more scores and/or one or more classifications, wherein the one or more scores and the one or more classifications are suitable for a business use of the service provider.

16. The method of claim 12 , further comprising providing feedback to the recommendation service at least when the verifiable output is not optimized for the business case.

17. The method of claim 16 , further comprising retraining the recommendation service based on the feedback.

18. A recommendation service comprising:

a plurality of servers, wherein each server in the plurality of servers includes a processor;

a computer storage medium that stores computer-executable instructions that are executable by each processor to at least implement:

a recommendation model configured to receive input of a user and convert the input into a full feature vector suitable for a business case of a service provider, wherein the input includes verifiable claims with private data of the user, wherein the verifiable claims are generated by one or more issuers in response to a request from the user;

a supervised model configured to generate a verifiable output from the full feature vector, wherein the verifiable output includes at least one of a score, a classification, or the full feature vector, wherein the verifiable output includes the private data of the user and data of other users, wherein the private data is chosen to be shared by the user and wherein the verifiable output is decoupled from the service provider, wherein the verifiable output is configured to enable the service provider to provide personalized services.

19. The recommendation service according to claim 18 , wherein the recommendation model is configured to generalize the user input when generating the full feature vector.