System and method for providing enhanced recommendations based on ratings of offline experiences

A method executed by at least one hardware processor comprising the steps of:

• receiving, using an interface operably coupled with the at least one hardware processor and configured to send and receive data over a network, messages from a first user to a second user;
• determining, based at least in part on the messages, that the first user and the second user had an in-person meeting, wherein determining that the first user and the second user had the in-person meeting comprises:
• applying an algorithm to the messages to determine a probability that the first user and the second user had an in-person meeting, wherein the algorithm is trained on a set of training data that comprises historical messages between multiple pairs of users, wherein each of the historical messages is labeled with whether the in-person meeting took place between a respective pair of users or not;
• extracting, by applying the algorithm, a set of attributes from the messages between the first user and the second user, wherein the set of attributes comprises at least one of:
• a frequency of messages exchanged between the first user and the second user,
• a number of messages exchanged between the first user and the second user,
• a timing of each message sent from the first user to the second user after the first user and the second user were matched,
• at least one certain keyword contained within the exchanged messages, or
• a day of a week when certain messages were exchanged between the first user and the second user;
• and
• assigning a set of weights to the set of attributes, wherein the set of weights indicates a degree of probability that the in-person meeting has occurred between the first user and the second user;
• and
• determining that the degree of probability is greater than a threshold;
• transmitting, using the interface, a request to the first user for a first set of data about the in-person meeting between the first user and the second user, the first set of data being associated with a survey comprising a set of questions;
• receiving, using the interface, the first set of data from the first user, the first set of data comprising one or more responses associated with the set of questions;
• determining, based at least in part on the first set of data, a score of the second user that indicates the first user's desire for a subsequent in-person meeting with the second user, wherein determining the score comprises:
• assigning a respective score to one or more categories of reasons for declining or accepting the subsequent in-person meeting;
• analyzing the one or more responses to determine a reason provided by the first user for declining or accepting the subsequent in-person meeting;
• and
• determining that the determined reason belongs to a category to which the score was assigned;
• in response to determining the score of the second user:
• updating a recommendation algorithm based on the score;
• and
• transmitting, using the interface, a notification, based on the score, to the first user;
• and
• generating, by executing the updated recommendation algorithm, an improved recommendation of a third user to the first user.