Not Available for Download

Clickprints on the Web: Are There Signatures in Web Browsing Data?

Posted: 27 Oct 2006  

Balaji Padmanabhan

University of Pennsylvania - Operations & Information Management Department

Yinghui (Catherine) Yang

Graduate School of Management, UC Davis

Date Written: February 2007

Abstract

We address the question of whether people have unique signatures - or clickprints - when they browse the Web. The importance of being able to answer this can be significant given applications to electronic commerce in general and in particular online fraud detection, a major problem in electronic commerce costing the economy billions of dollars annually. In this paper we present a general framework and specific formulations of this "unique clickprint determination problem". We explore one specific formulation for which we show how the unique clickprint determination problem can be cast more generally as an aggregation problem. To solve this we develop formal methods to determine the optimal amount of user data that must be aggregated before unique clickprints can be deemed to exist.

Suggested Citation

Padmanabhan, Balaji and Yang, Yinghui (Catherine), Clickprints on the Web: Are There Signatures in Web Browsing Data? (February 2007). Available at SSRN: https://ssrn.com/abstract=931057 or http://dx.doi.org/10.2139/ssrn.931057

Balaji Padmanabhan (Contact Author)

University of Pennsylvania - Operations & Information Management Department ( email )

Philadelphia, PA 19104
United States

Yinghui (Catherine) Yang

Graduate School of Management, UC Davis ( email )

One Shields Avenue
Davis, CA 95616

Paper statistics

Abstract Views
958