Abstract

Organizations often struggle with their efforts to implement data mining projects successfully. This is often due to the fact that they are influenced by success stories of others that glamorize the outcome of successful initiatives, while understating the persistent rigour and diligence required. Although process models exist for the knowledge discovery process their focus is often on outlining the activities that must be done and not on describing how they should be done. While there is some research in addressing how to carry out the various tasks in the phases, the data preparation phase is thought to be the most challenging and is often described as an art rather than a science. In this study we apply a multi-phased integrated knowledge discovery and data mining process model (IKDDM) to a data set from the financial sector and a present a new approach to data preparation for Sequential Patterns (SP) that facilitated the identification of customer focused patterns rather than products focussed patterns in the modelling phase.

Share

COinS