Techniques for estimating the computation and communication costs of Distributed Data Mining

Distributed Data Mining (DDM) is the process of mining distributed and heterogeneous datasets. DDM is widely seen as a means of addressing the scalability issue of mining large data sets. Consequently, there is an emerging focus on optimisation of the DDM process. In this paper we present cost formulae for estimating the communication and computation time for different distributed data mining scenarios. © 2002 Springer-Verlag Berlin Heidelberg.