Sampling technique selection framework for knowledge discovery

Knowledge Discovery in Databases (KDD) is a complex interactive and iterative process which involves many steps that must be done sequentially. Supporting the whole KDD process has enjoyed a great popularity in recent years, with advances in research. We however still lack of a generally accepted underlying framework and this hinders the further development of the field. We believe that the quest for such a framework is a promising research area. It is crucial to consider that the optimization of the mining process must take into account the pre-steps of knowledge discovery, thus a quite challenging problem is to consider an efficient method to estimate the optimal training set. In our work we aim in building an efficient knowledge discovery system for discovering interesting associations from databases, our approach improving. The utility of the data mining process by dividing the problem in two main tasks: sampling which considers The dataset to be mined and mining which considers the applied algorithm to mine the data.