Apriori Algorithm

The Apriori algorithm is used to solve association problems. Associations are calculated in two steps:

  1. Find all combinations of items, called frequent itemsets, whose support is greater than minimum support.
  2. Use the frequent itemsets to generate the desired rules.

Oracle Data Mining Association supports single-consequent rules only (for example, "if A and B then C").

The number of frequent itemsets is controlled by the minimum support parameter. The number of rules generated is controlled by the number of frequent itemsets and the confidence parameter. If either the confidence parameter or the support parameter is set too high, there may be frequent itemsets in the association model but no rules. In this case, modify one or more of the parameters and rebuild the model. First try decreasing minimum support; if that doesn't work, decrease minimum confidence. You may need to specify values less than 1 for either of these values.

Difficult Cases for Associations

The Apriori algorithm works by iteratively enumerating frequent itemsets of increasing lengths subject to the minimum support threshold. Since state-of-the-art algorithms for associations work by iterative enumeration, association rules algorithms do not handle the following cases efficiently:

The Apriori algorithm supports sparse data. However, you cannot build Association models using Data Miner if one of the input columns has mining type text; to build a model using this kind of input, you must use one of the Oracle Data Mining programmatic interfaces.

For more information, see Oracle Data Mining Concepts in Where to Find More Information.