Computing Association Rules Using Partial Totals (2001) [9 citations — 4 self]
|
Abstract:
The problem of extracting all association rules from within a binary database is well-known. Existing methods may involve multiple passes of the database, and cope badly with densely-packed database records because of the combinatorial explosion in the number of sets of attributes which must be considered. We present a new class of methods which use a single pass of the database to perform a partial computation of the totals required, and to store these partial totals in a structure which facilitates computation of the final totals. We describe generic algorithms for computing these totals for which storage and performance characteristics are examined. The method opens the way to a number of strategies for practical implementations, for which heuristics are discussed.
Citations
| 1607 | Fast Algorithms for Mining Association Rules – Agrawal, Srikant - 1994 |
| 285 | An Efficient Algorithm for Mining Association Rules in Large Databases – Savasere, Omiecinski, et al. - 1995 |
| 272 | Sampling Large Databases for Association Rules – Toivonen - 1996 |
| 252 | Efficiently mining long patterns from databases – Bayardo - 1998 |
| 194 | New Algorithms for fast discovery of association rules – Zaki, Ogihara, et al. - 1997 |
| 84 | Search through Systematic Set Enumeration – Rymon - 1992 |
| 63 | Set-oriented mining of association rules – Houtsma, Swami - 1993 |
| 54 | Mining Association Rules between – agrawal, Imielinski, et al. |
