Mixed-model recommender for leisure activities

A computer system for recommending leisure activities to a user, the computer system comprising:

• a processor;
• a memory;
• a receiving mechanism configured to receive at least one query for leisure activities, which are associated with a plurality of activity types;
• a collaborative rating mechanism configured to determine a collaborative rating of a candidate activity by other users;
• a preference determination mechanism configured to determine the user's preference for the candidate activity based on a soft query on a set of attributes associated with the candidate activity;
• an interest determination mechanism configured to determine the user's interest for the candidate activity based on the user's past behavior;
• a proximity determination mechanism configured to determine proximity of the candidate activity to the user's current location;
• a composite scoring mechanism configured to generate a composite score for the candidate activity based on the type of the candidate activity and a combination of the collaborative rating, the user's preference, the user's interest, and the proximity of the candidate activity;
• and
• a recommendation mechanism configured to recommend a list of leisure activities of different activity types based on composite scores of the leisure activities.

A computer readable storage medium storing instructions which when executed by a computer cause the computer to perform a method for recommending leisure activities to a user, the method comprising:

• receiving one query for leisure activities, which are associated with a plurality of activity types;
• determining by a computer a collaborative rating of a candidate activity by other users;
• determining by the computer the user's preference for the candidate activity based on a soft query on a set of attributes associated with the candidate activity;
• determining by the computer the user's interest in the candidate activity based on the user's past behavior;
• determining by the computer proximity of the candidate activity to the user's current location;
• generating by the computer a composite score for the candidate activity based on the type of the candidate activity and a combination of the collaborative rating, the user's preference, the user's interest, and the proximity of the candidate activity;
• and
• recommending to the user a list of leisure activities of different activity types based on composite scores of the leisure activities.