Exploring Set Recommendation from a Financial Perspective

摘要

All current recommendation algorithms try to handle the problem of recommending single item to a user. However, there are many cases that we need to consume a set of items at one time in our real life, e.g., many restaurants may provide some food set for users to choose and a travel agent may provide many travel routes or itineraries which can contain different interest places. In this paper, inspired by the modern portfolio theory, we propose three set recommendation algorithms which return a list of item-set for users. We conduct experiments on a real-life dataset by comparing the performance of our proposed approaches. The experimental results fit our expectation and show the effectiveness of proposed methods.