Title :
Multi Relational Rules Mining in Data Warehouse
Author_Institution :
Dept. of Comput. Eng., Huaiyin Inst. of Technol., Huaian
Abstract :
Multi relational rules mining is a new area of data mining research. There three kinds of algorithm currently. One is ILP approach, the second is AVL upgrading approach, and the last is mould a relational database into a single table to mine with traditionally single table technology. Due to the drawback of these methods, a new ideal to mine rules in data warehouse is proposed. The data schema constructing, primitive language and mining algorithm are analysis. The algorithm concerns the rules from one table to another only, but considers the single tablepsilas rules. The experiments show it has a good accuracy due to utilize the relational information in data warehouse.
Keywords :
data mining; data warehouses; data mining; data warehouse; multi relational rules mining; Algorithm design and analysis; Bayesian methods; Cities and towns; Data engineering; Data mining; Data warehouses; Decision trees; Electronic mail; Knowledge engineering; Relational databases; data schema; data warehouse; multi relational rules;
Conference_Titel :
Knowledge Discovery and Data Mining, 2009. WKDD 2009. Second International Workshop on
Conference_Location :
Moscow
Print_ISBN :
978-0-7695-3543-2
DOI :
10.1109/WKDD.2009.143
