DataBase and Data Mining Group

• Huge amount of data
• Most algorithms exploit ad-hoc main memory data structures to efficiently perform data mining
  • These approaches rely on the available physical memory and may run out of memory when the analysis is performed on very large databases

Goal

• design of disk-based structures and algorithms to efficiently support clustering algorithms
• data mining optimizer to automatically select appropriate  algorithms and data access methods for frequent  itemset mining
• text mining by exploiting data mining techniques   (e.g., clustering, association rules) in different application domain
• study of parallel and distributed algorithms to scale itemset mining