Techniques for device configuration of prospective contacts using messaging history information

1. A computer-implemented method, comprising:

determining a prospective contact list for a user account for a communication system, the prospective contact list comprising a plurality of prospective contacts wherein the prospective contact list is generated based on a union of two or more of a contact-of-contact list for the user account, a soft-match list for the user account where an unverified predicted phone number for the user account matches a phone number address book for a one of the prospective contacts, a reverse-contact list for the user account, and a short-message-service-match list for the user account;

determining a predicted communication interest for each prospective contact on the prospective contact list for the user account, wherein, for each prospective contact, the predicted communication interest comprises a prediction of interest in messaging with the prospective contact using the user account;

determining a ranking weight for each prospective contact on the prospective contact list based on the predicted communication interest for each prospective contact; and

ordering the prospective contact list for display for the user account based on the determined ranking weight for each prospective contact on the prospective contact list.

2. An apparatus, comprising:

a processor circuit on a device;

a client front-end component operative on the processor circuit to receive a client inbox request for a user account from a client device, the user account for a communication system; and send an ordered prospective contact list to the client device in response to the client inbox request, the ordered prospective contact list ordered for display for the user account based on a determined ranking weight for each prospective contact on the ordered prospective contact list;

a prospective contact list component operative to generate a prospective contact list for a user account for a communication system based on a user repository for the communication system, the prospective contact list comprising a plurality of prospective contacts, wherein generating the prospective contact list for the user account excludes any existing contacts from an existing contact list for the user account and wherein the prospective contact list is generated based on a union of two or more of a contact-of-contact list for the user account, a soft-match list for the user account where an unverified predicted phone number for the user account matches a phone number address book for a one of the prospective contacts, a reverse-contact list for the user account, and a short-message-service-match list for the user account;

a predicted interest component operative to determine a predicted communication interest for each prospective contact on the prospective contact list for the user account, wherein, for each prospective contact, the predicted communication interest comprises a prediction of interest in messaging with the prospective contact using the user account; and

a contact ranking component operative to determine a ranking weight for each prospective contact on the prospective contact list based on the predicted communication interest for each prospective contact list.

3. At least one computer-readable storage medium comprising instructions that, when executed, cause a system to:

generate a prospective contact list for a user account for a communication system based on a user repository for the communication system, the prospective contact list comprising a plurality of prospective contacts, wherein generating the prospective contact list for the user account excludes any existing contacts from an existing contact list for the user account and wherein the prospective contact list is generated based on a union of two or more of a contact-of-contact list for the user account, a soft-match list for the user account where an unverified predicted phone number for the user account matches a phone number address book for a one of the prospective contacts, a reverse-contact list for the user account, and a short-message-service-match list for the user account;

determine a predicted communication interest for each prospective contact on the prospective contact list for the user account, wherein, for each prospective contact, the predicted communication interest comprises a prediction of interest in messaging with the prospective contact using the user account;

determine a ranking weight for each prospective contact on the prospective contact list based on the predicted communication interest for each prospective contact; and

order the prospective contact list for display for the user account based on the determined ranking weight for each prospective contact on the prospective contact list.

4. The method of claim 1 , further comprising:

generating the prospective contact list based on a user repository for the communication system, wherein generating the prospective contact list for the user account excludes any existing contacts from an existing contact list for the user account.

5. The method of claim 1 , further comprising:

ordering the prospective contact list for display to the user account in association with a messaging interface for the communication system.

6. The method of claim 1 , further comprising:

generating a relationship count for each prospective contact of the prospective contact list, wherein the relationship count for each prospective contact measures whether each prospective contact possesses each of a contact-of-contact relationship, a soft-match relationship, a reverse-contact-list relationship, and a short-message-service-match relationship; and

determining the ranking weight based on the relationship count.

7. The method of claim 1 , wherein the predicted communication interest is based on a linear function of two or more of a contact-of-contact relationship, a soft-match relationship, a reverse-contact-list relationship, a short-message-service-match relationship, and a contact coefficient, wherein the contact coefficient is generated based on social-networking information from a social-networking system.

8. The method of claim 1 , wherein a confidence strength score is associated with each contact on the soft-match list.

9. The apparatus of claim 2 , further comprising:

the predicted interest component operative to generate a relationship count for each prospective contact of the prospective contact list, wherein the relationship count for each prospective contact measures whether each prospective contact possesses each of a contact-of-contact relationship, a soft-match relationship, a reverse-contact-list relationship, and a short-message-service-match relationship; and

the contact ranking component operative to determine the ranking weight based on the relationship count, wherein prospective contacts with equal relationship count are ranked relative to a contact coefficient, wherein the contact coefficient is generated based on social-networking information from a social-networking system.

10. The apparatus of claim 2 , wherein the predicted communication interest is based on a linear function of two or more of a contact-of-contact relationship, a soft-match relationship, a reverse-contact-list relationship, a short-message-service-match relationship, and a contact coefficient, wherein the contact coefficient is generated based on social-networking information from a social-networking system, the linear function determined based on a linear regression of a historical data set for the communication system, the linear regression based on a predicted communication interest model, the predicted communication interest model predicting one or more of an existence of communication interaction between the user account and a prospective contact, a duration of communication interaction between the user account and the prospective contact, a user contact future communication activity measure, and a user contact future engagement measure.

11. The apparatus of claim 2 , wherein a confidence strength score is associated with each contact on the soft-match list.

12. The computer-readable storage medium of claim 3 , comprising further instructions that, when executed, cause a system to:

generate a relationship count for each prospective contact of the prospective contact list, wherein the relationship count for each prospective contact measures whether each prospective contact possesses each of a contact-of-contact relationship, a soft-match relationship, a reverse-contact-list relationship, and a short-message-service-match relationship; and

determine the ranking weight based on the relationship count, wherein prospective contacts with equal relationship count are ranked relative to a contact coefficient, wherein the contact coefficient is generated based on social-networking information from a social-networking system.

13. The computer-readable storage medium of claim 3 , wherein the predicted communication interest is based on a linear function of two or more of a contact-of-contact relationship, a soft-match relationship, a reverse-contact-list relationship, a short-message-service-match relationship, and a contact coefficient, wherein the contact coefficient is generated based on social-networking information from a social-networking system, the linear function determined based on a linear regression of a historical data set for the communication system, the linear regression based on a predicted communication interest model, the predicted communication interest model predicting one or more of an existence of communication interaction between the user account and a prospective contact, a duration of communication interaction between the user account and the prospective contact, a user contact future communication activity measure, and a user contact future engagement measure.

14. The computer-readable storage medium of claim 3 , wherein a confidence strength score is associated with each contact on the soft-match list.

15. The method of claim 6 , wherein prospective contacts with equal relationship count are ranked relative to a contact coefficient, wherein the contact coefficient is generated based on social-networking information from a social-networking system.

16. The method of claim 7 , the linear function determined based on a linear regression of a historical data set for the communication system.

17. The method of claim 16 , the linear regression based on a predicted communication interest model, the predicted communication interest model predicting one or more of an existence of communication interaction between the user account and a prospective contact, a duration of communication interaction between the user account and the prospective contact, a user contact future communication activity measure, and a user contact future engagement measure.