Mining databases with different schemas: integrating incompatible classifers

摘要: Distributed data mining systems aim to discover (and combine) usefull information that is distributed across multiple databases. The JAM system, for example, applies machine learning algorithms compute models over sets and employs meta-learning techniques combine the models. Occasionally, however, these (or classifiers) are induced from databases have (moderately) different schemas hence incompatible. In this paper, we investigate problem of combining computed with schemas. Through experiments performed on actual credit card provided by two financial institutions, evaluate effectiveness proposed approaches demonstrate their potential utility.