|Conference: KESDA'98, Knowledge Extraction from Statistical Data |
Organized by: Eurostat
Field: Statistics, Computer Science, Pattern Recognition, Artificial Intelligence, Data analysis
Language(s): english, french, german
Description: Statistical Offices gather ever more, larger, and more complex data sets as Official Statistics. There is, therefore, a growing need for the automatic analysis and summarisation of these data sets. Symbolic Data Analysis and Data Mining are the two major approaches towards this goal.
Symbolic Data Analysis is the generalisation of standard data analysis to Symbolic Data Tables. Symbolic Data Tables are tables in which the cells contain complex information, such as subsets, intervals, histograms, probability distribution and dependencies. These tables are generated from the original data sets as a summarisation that keeps as much of the initial information as possible.
Knowledge Discovery in Databases is the nontrivial process of identifying valid, novel, potentially useful, and ultimately understandable patterns in data. Data mining is the analysis step in this process, and it can be defined as the induction of understandable models from a database. Examples, of such models are Decision Trees, Association Rules and Interesting Subsets.
The main Objective of the Conference is to promote NEW METHODS in Data Mining and Symbolic Data Analysis for Statistical Data Sets.
URL 1: Conference Info
E-mail 1: Organizer