Recently, recommender systems that recommend items which match the users’ preferences are widely used for online shopping. In particular, collaborative filtering methods are often used to make recommendations to a particular user, because they provi...
Recently, recommender systems that recommend items which match the users’ preferences are widely used for online shopping. In particular, collaborative filtering methods are often used to make recommendations to a particular user, because they provide a list of suggested items that are similar to those previously preferred by the user by considering other users’ trading records. However, the collaborative filtering methods are limited to make the recommendations for general consumer goods. For example, in the case of stock markets, these methods may recommend to the users who traded on stocks with a low rate of return only the stocks with a similar rate of return. In this paper, we propose a stock market portfolio recommender system(a recommender system for stock markets) by transforming the collaborative filtering for implicit feedback datasets to overcome the limitations.