Wednesday, March 7, 2012

Where do I find a server log file to implement a Data Mining Algorithm I'm working on?

Server log files are not easy to find since privacy is an issue. Are there any sites or groups that make these files available for academic purposes?

If not, what are my other options?Where do I find a server log file to implement a Data Mining Algorithm I'm working on?
Unforturnately i have no idea why accessing server log files would be a problem. Would it be because you dont have access to systems of all the kinds (and persons with access for them)? Or you need more data than such test systems would provide? Or you mean that they dont want to give you real person account information, IP addresses etc? Unforturnately i don't know more than Google search about such downloadables but can't see why you would need huge data amounts just to develop an algorithm to pick out and collect important information. Just produce a sample yourself and, if you must, replace sensitive data with something you choose (in all records so analysis matches).

Keep in mind also that for instance Windows event log files are binary and usually used via API's.

No comments:

Post a Comment