Application of decision-tree induction techniques to personalized advertisements on Internet storefronts

Customization and personalization services are a critical success factor fo r Internet stores and Web service providers. This paper studies personalize d recommendation techniques that suggest products or services to the custom ers of Internet storefronts based on their demographics or past purchasing behavior. The underlining theories of recommendation techniques are statist ics, data mining, artificial intelligence, and rule-based matching. In the rule-based approach to personalized recommendation, marketing rules For per sonalization are usually obtained from marketing experts and used to perfor m inferencing based on customer data. However, it is difficult to extract m arketing rules from marketing experts, and to validate and maintain the con structed knowledge base. This paper proposes a marketing rule-extraction te chnique For personalized recommendation on Internet storefronts using machi ne learning techniques, and especially decision-tree induction techniques. Using tree induction techniques, data-mining tools can generate marketing r ules that match customer demographics to product categories. The extracted rules provide personalized advertisement selection when a customer visits a n Internet store. An experiment is performed to evaluate the effectiveness of the proposed approach with preference scoring and random selection.