The feature selection requires a special notice because it helps in the selection of the attributes that will be effective in the analysis. It also helps in the rejection of the attributes that are either too noisy or are very insignificant in the analysis. Hence, the feature selection mostly involves the selection of appropriate attributes. A default feature selection is done automatically based on the model selected, the data types of the attributes, and the parameters (if any) that might be set up while designing the model. Every attribute that is designated to be a part of the model is assigned a score; the score threshold is also modifiable. The feature selection comprises of various methods that depends on whether the data is continuous or discrete. For continuous data, we use the interestingness score to select the columns that are more closely related, whereas for discrete methods, we use Shannon's entropy, Bayesian algorithm with K2 Prior, and the Bayesian...