Personalized Web-page Rendering System

Personalized rendering of web pages gives the users greater control to view only what they prefer. The goal of this work is to provide a tool that will let users customize the content on the pages. Our proposed model architecture learns user preferences through interaction and eventually learns to block content that is not of interest, or is offensive, to the user. This learning from interaction is achieved through a combination of reinforcement learning and data mining techniques. In this paper we look at customizing the rendering of advertisements. We provide the user a tool that customizes itself to their preferences, and blocks irrelevant advertisements and allow only those that are of interest to the user. We also demonstrate empirically that our tool customizes itself to hypothetical hand crafted users.