Induction and deduction are two opposite operations in data-mining applicat
ions. Induction extracts knowledge in the form of, say, rules or decision t
rees from existing data, and deduction applies induction results to interpr
et new data. An intelligent learning database (ILDB) system integrates mach
ine-learning techniques with database and knowledge base technology. It sta
rts with existing database technology and performs both induction and deduc
tion. The integration of database technology, induction (from machine learn
ing), and deduction (from knowledge-based systems) plays a key role in the
construction of ILDB systems, as does the design of efficient induction and
deduction algorithms. This article presents a system structure for ILDB sy
stems and discusses practical issues for ILDB applications, such as instanc
e selection and structured induction.