A Discrete Formulation of a Unified Data Mining Model

A race is going on to process the complex and huge amount of data. To achieve this, data analytics are proposing different models and methods. Parallel to this, rich research work has been done to simplify different mathematical models for the validation and for the acceptance level of calculated knowledge. In this paper, we propose a discrete formulation of a unified data mining model. It envisages that knowledge extraction is a multi-step process where different data mining processes such as clustering, classification and visualization are unified in a cascade way; that is, an output of a process is the input to another process which helps to achieve scalability and flexibility on a larger scale. Simultaneously, to prove whether our proposed model is valid or invalid, it is evaluated by discrete structure. For this, different mathematical formulations are formed to support the cause and then these mathematical formulations are evaluated to achieve the required target. Each mathematical formulation is examined in detail by using a simple technique called Truth Table and its Truth Values. Truth Table shows that evaluated mathematical formulations are valid and correct.