Mining Generalized Association Rules and Sequential Patterns Using SQL Queries

Database integration of mining is becoming increasingly important with tile installation of larger and larger data warehouses built around relational database technology. Most of the commercially available miningsystemsintegrate loosely (typically, through an ODBCor SQLcursor interface) with data stored in DBMSs.In cases wherethe mining algorithm makesnmltiple passesover the data, it is also possible to cachethe data in fiat files rather than retrieve multiple times from the DBMS,to achieve better performance.Recentstudies have found that for association rule mining,withcarefully tunedSQLforinulations it is possible to achieve performancecomparableto systems that cachethe data in files outside the DBMS.TheSQL implementationhas potential for offering other qualitaUveadvantageslike automatic parallehzation, developmentease, portability and inter-operability with relational operators. In"this paper, wepresent several alternatives for formulatingas SQLqueries association rule general...

• Type: Conference
• Year: 1998
• Where: KDD
• Authors: Shiby Thomas, Sunita Sarawagi
• Keywords: Association Rule, Data Mining, KDD 1998, Larger Data Warehouses, Mining Algorithm Makesnmltiple