SEVERAL YEARS as a college lecturer have taught me how to recognise the person who wrote an essay in a final examination without reading the name on the front of the exam book. It's well known that people can be identified from the way they write. It takes churning through three or four submission of at least 300 words each before I can tell a Mulley from a Raftery. You only need one pass to distinguish Twenty Major from Waggie. Many bloggers pick up the technique after two or three passes as well. You can also be categorised and identified by what you view. Balaji Padmanabhan and Catherine Yang claim that people using the internet can also be identified by their surfing behaviour. They explain this in the Wharton Business School's Knowledge@Wharton:
The authors conclude that by observing these patterns, an e-commerce company can distinguish between two individuals with nearly 100% accuracy, sometimes with as few as three Internet sessions, and potentially use that information to deter fraud. The number of sessions needed to identify an individual rises with the number of unique users a site has because there are more people to differentiate.
While Padmanabhan and Yang focus on whether individuals have clickprints, the number of sessions needed to identify a unique individual, and potential fraud prevention applications, the paper also shows how companies can track users just by watching behavior. "Our main finding is that even trivial features in an Internet session can distinguish users," says Padmanabhan. "People do seem to have individual browsing behaviors."
Once you know how someone browses, you can look for those patterns and generate an alert on them in real time. For example, if you're prone to using your mobile phone to browse for racing results followed by local news followed by blog browsing, anytime a browsing pattern like that wrote itself to a log file in a mobile phone network data centre, you could cross-reference that activity to all phones connected to the centre. You'd most likely find others connected to the same cell tower who are affiliated to the person who was browsing.
Clickstream analysis also pertains to finding people who jump between cybercafes while doing their business. Similar browsing histories would alert snoops to the physical presence of a specific person.
Clickprints also help prevent fraud. Amazon knows my account details and my purchase patterns. Consequently, Amazon often lets me purchase things online even without checking whether I have available credit on my card. They really don't care because I have accumulated several years of consistent use and regular payments.
Jack Schofield -- "Can you be identified by your clickprint?"
