Database Knowledge Discovery Combining Cluster Analysis and Classification Using Data Mining

Two key data mining methods are clustering and classification. The problem of classification involves categorizing object into one-to-many pre-established categories according to the characteristics of the object. While clustering groups objects based on their proximity or similarity and is a clear learning problem. Every group is referred to as a cluster. In the study, we perform integration to data mining by the clustering and classification techniques using a big database called the “Fisher's Iris Dataset” with the attribute and some examples. Using the Data Mining application Waikato Environment for Knowledge Analysis, We contrasted the outcomes of integrating a clustering and classification technique based on numerous criteria with the outcomes of a straightforward classification strategy (using the J48 classifier). The experiment's findings demonstrate that combining clustering and classification produces effective outcomes with a high robustness and accuracy rate, and the data set contains some values that are missing.