Abstract: With the development of e-business, more and more gas appliances are transacted in Internet. Personalized recommendation problem becomes more and more important for individual users with different preferences. The objective of this research is to propose a user-based personalized recommendation model for gas appliances. This recommendation model is based on collaborative filtering algorithm, which is mainly divided into two parts. The first part is to obtain similar users of target user and preferred products of the target user, according to the registration information of target users and the their historical preferences for products. The second part is to formulate the purchase preference evaluation criteria of target users and evaluate the performances of preferred products with respect to evaluation criteria. Finally, experiments are conducted to verify the feasibility and efficiency of the proposed recommendation model.