Serving Comparative Shopping Links Non-invasively

We propose a simple, user-friendly tool which aims to offer comparative shopping to the consumer with minimal distraction. The key idea is to detect whether a specific Web-page is commercial, i.e., whether it sells an individual product or service. The detection is performed in real-time at the client with focus on exceptionally low false positives. For each commercial page, we identify the product name $P$ from its hypertext and send $P$ to a knowledge server which responds with a list $mathbb{L}$ of URLs at which $P$ is sold in increasing order of pricing. The browser then presents $mathbb{L}$ in an non-invasive fashion to the user, resulting in a simple and effective shopping experience. We present certain statistical properties of collected commercial Web-pages, introduce a novel classifier for Boolean spaces, and compare its performance to SVM-QP.