Profiling Task
(Redirected from profiling task)
Jump to navigation
Jump to search
A Profiling Task is a Summarization Task that summarizes some Thing (Entity or Relation).
- AKA: Profiling Practice.
- Example(s):
- See: ETL Task.
References
2009
- http://en.wikipedia.org/wiki/Profiling_practices
- One of the most challenging problems of the information society is dealing with the increasing data overload. Due to the digitalization of all sorts of content and due to the improvement and drop in cost of recording technologies, the amount of available information is enormous and is increasing exponentially. It has thus become important for companies, governments and individuals to be able to discriminate information from noise, detecting those data that are useful or interesting. The development of profiling technologies must be seen against this background. These technologies are thought to efficiently collect and analyse data in order to find or test knowledge in the form of statistical patterns between data. This process is called Knowledge Discovery in Databases (KDD) Template:Harv, which provides the profiler with sets of correlated data that are used as “profiles”.
- Profiling practices refer to the whole process of construction and application of profiles, as defined above. This entry focuses on profiles that have been generated by computerized profiling technologies. What characterizes profiling technologies is the use of algorithms or other mathematical techniques that allow one to discover patterns or correlations in large quantities of data, aggregated in data bases. When these patterns or correlations are used to identify or represent people they can be called profiles. Other than a discussion of profiling technologies or population profiling the notion of profiling practices is not just about the construction of profiles but also concerns the application of group profiles to individuals, e.g. in the case of credit scoring, price discrimination or identification of security risks.
- Profiling is a matter of computerized pattern recognition, profiling practices enable refined price-discrimination, targeted servicing, detection of fraud, extensive social sorting. Real time machine profiling constitutes the precondition for emerging socio-technical infrastructures envisioned by advocates of Ambient intelligence, Autonomic Computing Template:Harv and Ubiquitous computing.