Data mining holds the promise of extracting unsuspected information from very large databases. One difficulty is that discovery techniques are often drawn from methods in which the amount of work increases geometrically with data quantity. Consequentially, the use of these methods is problematic in very large databases. Categorically based association rules are a linearly complex data mining methodology. Unfortunately, rules formed from categorical data often generate many fine grained rules. The concern is how fine grained rules might be aggregated and the role that non-categorical data might have. It appears that soft computing techniques may be useful.
展开▼