Classification

What is Classification?

Classification is defined as the process of recognizing, understanding, and grouping objects and ideas into preset categories. With the help of these pre-categorized training datasets, classification in machine learning programs leverages a wide range of algorithms to classify future datasets into respective and relevant categories. Classification algorithms used in machine learning utilize input training data to predict the likelihood or probability that the data that follows will fall into one of the predetermined categories.
In short, classification is a form of pattern recognition.

Regression VS Classification

• Regression : Used to predict continuous real values.
• Classification : Used to predict categories or classes.
  
  

Pros and Cons of Classification Models

Classification Model	Pros	Cons
Logistic Classification	Probabilistic approach. Provides information on the statistical significance of features.	Logistic Regression Assumption.
K Nearest Neighbors(KNN)	easy to understand. fast and effective.	The number of neighbors k must be determined.
Support Vector Machine(SVM)	Ideal. Unbiased to outliers. Not sensitive to overfitting.	Not suitable for non-linear data sets. Not effective for datasets with many features.
Kernel Support Vector Machine(Kernel SVM)	High performance on nonlinear datasets. Not prone to outliers. Not sensitive to overfitting.	Not effective for datasets with many features. complicated.
Naive Bayes	Effective. Unbiased to outliers. Suitable for nonlinear datasets. probabilistic approach.	It should be based on the fact that the features have the same statistical relevance.
Decision Tree Classification	Interpretability No feature scaling required. Works with both linear and non-linear data sets.	Worst results on small datasets. Overfitting occurs frequently.
Random Forest Classification	Powerful and precise. Shows good performance on non-linear datasets.	Uninterpretable. Overfitting easily occurs. You must select the number of trees.