A Conceptual Model of Personalized Pricing Recommender System Based on Customer Online Behavior

Recommender systems in the last decade opened new interactive channels between buyers and sellers leading to new concepts involved in the marketing strategies and remarkable positive gains in online sales. Businesses intensively aim to maintain customer loyalty, satisfaction and retention; such strategic longterm values need to be addressed by recommender systems in a more tangible and deeper manner. The reason behind the considerable growth of recommender systems is for tracking and analyzing the buyer behavior on the one to one basis to present items on the web that meet his preference, which is the core concept of personalization. Personalization is always related to the relationship between item and user leaving out the contextual information about this relationship. User's buying decision is not only affected by the presented item, but also influenced by its price and the context in which the item is presented, such as time or place. Recently, new system has been designed based on the concept of utilizing price personalization in the recommendation process. This system is newly coined as personalized pricing recommender system (PPRS). We propose personalized pricing recommender system with a novel approach of calculating consumer online real value to determine dynamically his personalized discount, which can be generically applied on the normal price of any recommend item through its predefined discount rules.