Method of increasing information pertinence for e-commerce recommender systems based on implicit data

The paper describes the method of increasing pertinence of information in e-commerce recommender systems based on implicit data, i. e., due to the processing of user activity associated with the decision-making process. The method works successfully in situations where information about user activity is absent or little informative. Practical application of this method in e-commerce systems can improve their efficiency through targeted supply of goods and services to consumers. The main feature of the proposed method is the combined use of Item–Item CF (collaborative filtering) and User–User CF methods taking into account the implicit data collected. The features of the proposed method are verified by a prototype software that is installed on the existing online store Thaisoap.