A Personalized Stock Recommendation System using Adaptive User Modeling

In this paper, a new framework for personalized stock recommendation system based on adaptive user models is presented. The system is designed to provide personalized and appropriated information to the investors based on their personal profiles and their historical system interactions. The system components include initializing and updating user models, monitoring the interaction of the user to the system, tailoring the information to meet the user's behavior and investment styles. The system prototype was implemented in JAVA. The system evaluations were performed on both synthetic subjects and real human subjects. The results show our proposed system is able to rapidly self-adapted to provide appropriate advice to each user who has a wide variety of interest, backgrounds and expertise