出版社：Centro Latinoamericano de Estudios en Informática
摘要：Knowledge Discovery in Databases (KDD), as any organizationalprocess, is carried
out beneath a Knowledge Management (KM)model adopted (even informally) by a
corporation. KDD isgrossly described in three steps: pre-processing, data
mining, andpost-processing. The latter is mainly related to the task
oftransforming in knowledge the patterns issued in the data miningstep. On the
other hand, KM comprises the following phases, inwhich knowledge is the subject
of the actions: identification ofabilities, acquisition, selection and
validation, organization andstorage, sharing, application, and creation.
Although there aremany overlaps between KDD and KM, one of them is
broadlyrecognized: the point in which knowledge arises. This paperconcerns a
study aimed at clarifying relations between theoverlapping areas of KDD and
knowledge creation, in KM. Thework is conducted by means of a case study using
the data fromthe Electoral Court of the Federal District (ECFD), Brazil.
Thestudy was developed over a 1.717.000-citizens data set fromwhich data mining
models were built by applying algorithms fromWeka. It was observed that,
although the importance ofInformation Technology is well recognized in the KM
realm, thetechniques of KDD deserve a special place in the knowledgecreation
phase of KM. Moreover, beyond the overlap of post-processing and knowledge
creation, other steps of KDD cancontribute significantly to KM. An example is
the fact that oneimportant decision taken from the ECFD board was taken on
thebasis of a knowledge acquired from the pre-processing step ofKDD.
