Capacity-constrained recommendation system

A recommendation system, comprising:

• one or more processors;
• and
• a memory storing instructions that, when executed by the one or more processors, causes the recommendation system to perform operations including:
• determining a plurality of contribution values based on interactions between a plurality of users and a plurality of items, each of the plurality of contribution values representing a preference of a respective user for a respective item;
• determining a capacity of each of the plurality of items, the capacity of each item representing a maximum number of users to which the item can be recommended;
• and
• recommending one or more items of the plurality of items to each of the plurality of users based at least in part on the plurality of contribution values and the capacities of the plurality of items.

A method of recommending items to users of a recommendation system, the method performed by one or more processors and comprising:

• determining a plurality of contribution values based on interactions between a plurality of users and a plurality of items, each of the plurality of contribution values representing a preference of a respective user for a respective item;
• determining a recommendation limit associated with the recommendation system, the recommendation limit representing a maximum number of items that can be recommended to each of the plurality of users;
• determining a capacity of each of the plurality of items, the capacity of each item representing a maximum number of users to which the item can be recommended;
• and
• recommending one or more items of the plurality of items to each of the plurality of users based at least in part on the plurality of contribution values, the recommendation limit, and the capacities of the plurality of items.