Systems and methods for peer-to-peer recommendation processing

A system, including:

• one or more processors;
• and
• memory including instructions that, as a result of being executed by the one or more processors, cause the system to:
• receive a request to solicit a set of users for new music recommendations, wherein the request specifies information indicative of types of music being solicited, and wherein the request is associated with a user;
• dynamically train a machine learning algorithm to continuously update a set of profiles corresponding to different users as songs are shared amongst the different users and as feedback corresponding to the songs is received;
• automatically and continuously update tastes in music for the different users as the feedback is received, wherein the tastes in music are associated with the set of profiles corresponding to the different users;
• determine a set of respondent profiles corresponding to a set of respondent users by using a user profile corresponding to the user as input to the machine learning algorithm;
• transmit the request, wherein when the request is received at the set of respondent users, a subset of the set of respondent users provides newly generated responses, and wherein a newly generated response includes a new song selected by a respondent user;
• evaluate the newly generated responses to identify one or more relevant new songs newly provided by one or more respondent users from the subset, wherein the newly generated responses are evaluated according to the request and different song profiles corresponding to different songs provided in the newly generated responses;
• present the one or more relevant new songs when the one or more relevant new songs are received at the user and the set of respondent users;
• receive new feedback from one or more recipients of the one or more relevant new songs, wherein the new feedback includes different interactions with the one or more relevant new songs by the one or more recipients;
• automatically update the machine learning algorithm as the set of profiles are continuously updated and as the new feedback is received, wherein the machine learning algorithm is automatically updated using the request, the one or more relevant new songs, and the new feedback as the new feedback is received;
• update a set of song profiles corresponding to the one or more relevant new songs as the new feedback is received, wherein the set of song profiles are updated to create associations amongst the one or more relevant new songs, the set of profiles, and requests for different music recommendations;
• and
• automatically generate updated tastes in music for the user and the set of respondent users, wherein the updated tastes in music are automatically generated by the machine learning algorithm as the new feedback is received.

A non-transitory computer-readable storage medium storing thereon executable instructions that, as a result of being executed by one or more processors of a computer system, cause the computer system to:

• receive a request to solicit a set of users for new music recommendations, wherein the request specifies information indicative of types of music being solicited, and wherein the request is associated with a user;
• dynamically train a machine learning algorithm to continuously update a set of profiles corresponding to different users as songs are shared amongst the different users and as feedback corresponding to the songs is received;
• automatically and continuously update tastes in music for the different users as the feedback is received, wherein the tastes in music are associated with the set of profiles corresponding to the different users;
• determine a set of respondent profiles corresponding to a set of respondent users by using a user profile corresponding to the user as input to the machine learning algorithm;
• transmit the request, wherein when the request is received at the set of respondent users, a subset of the set of respondent users provides newly generated responses, and wherein a newly generated response includes a new song selected by a respondent user;
• evaluate the newly generated responses to identify one or more relevant songs newly provided by one or more respondent users from the subset, wherein the newly generated responses are evaluated according to the request and different song profiles corresponding to different songs provided in the newly generated responses;
• present the one or more relevant songs to when the one or more relevant new songs are received at the user and the set of respondent users;
• receive new feedback from one or more recipients of the one or more relevant new songs, wherein the new feedback includes different interactions with the one or more relevant new songs by the one or more recipients;
• automatically update the machine learning algorithm as the set of profiles are continuously updated and as the new feedback is received, wherein the machine learning algorithm is automatically updated using the request, the one or more relevant new songs, and the new feedback as the new feedback is received;
• update a set of song profiles corresponding to the one or more relevant new songs as the new feedback is received, wherein the set of song profiles are updated to create associations amongst the one or more relevant new songs, the set of profiles, and requests for different music recommendations;
• and
• automatically generate updated tastes in music for the user and the set of respondent users, wherein the updated tastes in music are automatically generated by the machine learning algorithm as the new feedback is received.