DOI: 10.17705/1CAIS.00506
关键词: Genetic programming 、 Real life data 、 Production (economics) 、 Ground-penetrating radar 、 Domain (software engineering) 、 Specific knowledge 、 Data mining 、 Business rule 、 Computer science
摘要: This paper proposes an inductive data mining technique (named GPR) based on genetic programming. Unlike other systems, the particularity of our is its ability to discover business rules that satisfy multiple (and possibly conflicting) decision or search criteria simultaneously. We present a step-by-step method implement GPR, and introduce prototype generates production from real life data. also report in this article use GPR organization seeks understand how employees make decisions “voluntary separation" program. Using personnel database 12,787 with 35 descriptive variables, able employees’ hidden making patterns form rules. As approach does not require any domain specific knowledge, it can be used without major modification different domains.