Personalized recommendation has important implications in raising online shopping efficiency and increasing product sales. There has been wide interest in finding ways to provide more efficient personalized recommendations. Most existing studies focus on how to improve the accuracy and efficiency of the recommendation algorithms or are more concerned on ways to reduce perceived risks and thus increase consumer satisfaction. Unlike these studies, our study begins from the decision‐making process of consumers, using consumers' two‐stage decision‐making system and preference inconsistency theory as a basis, to reveal the mechanisms involved in consumers' acceptance of recommendations. This paper analyzes the effect of personalized recommendations from two angles, recommendation timing and product portfolio, tries to point out differences in consumer preferences between similar products and related products, and verifies that consumers demand diversity in the recommended content. The study analyzes differences in the acceptance of personalized recommendations between practical products and hedonic products and discovers that recommendations of hedonic products are more effective than that of practical products. Based on the research earlier, the study provides suggestions on how to better plan and operate a personalized recommendation system. Copyright © 2016 John Wiley & Sons, Ltd.