A Smart Hybrid Data Mining Technique for Improving Classification Accuracy in Complex Data Sets
Enterprise data mining applications, such as mining public service data and telecom fraudulent activities, inevitably involve complex data sources, particularly multiple large scale, distributed, and heterogeneous data sources embedding information about business transactions, user preferences, and business impact. In these situations, business people certainly expect the discovered knowledge to present a full picture of business settings rather than one view based on a single source. To handle these said complex data forms, there are various methods such as joining multiple relational tables have been proposed, it is not possible, and to join relevant large data sources for mining patterns consisting of multiple aspects of information. So these techniques are having Time and Space complexity.