Product recommendation methods have become the cornerstone of electronic commerce platforms due to their ability to solve the information overload problem and inform customers about their potentially interesting products. However, previous recommendat...
Product recommendation methods have become the cornerstone of electronic commerce platforms due to their ability to solve the information overload problem and inform customers about their potentially interesting products. However, previous recommendation methods fail to consider customers’ price preferences, which are essential in recommending suitable products. To bridge this gap, this study proposes a hybrid recommendation method that combines customer behaviors, product content, and price preferences for product recommendations. In the proposed method, two strategies are designed to model customers’ price preferences. The proposed method is evaluated with a real-world data set and compared with three baseline methods. The evaluation results show that the proposed recommendation method with either strategy significantly outperforms the three baseline methods in terms of precision, recall. F-score, and mean average precision (MAP) measures.