Machine Learning Model

This is the types of machine learning model and their usage.

Linear Regression

Models the relationship between the dependent variable and independent variables as a linear equation.

Logistic Regression

Used for categorical dependent variables, predicting probabilities by fitting data to a logistic curve.

Polynomial Regression

Models the relationship as an nth degree polynomial, suitable for non-linear relationships.

Ridge Regression

Addresses multicollinearity by adding a penalty term to shrink coefficients.

Lasso Regression

Adds a penalty term using absolute coefficients, aiding feature selection by setting some coefficients to zero.

ElasticNet Regression

Combines penalties of ridge and lasso regression, beneficial for correlated features.

Bayesian Regression

Utilizes Bayesian inference for parameter estimation, providing a probabilistic framework.

Nonlinear Regression

Fits a curve using nonlinear functions for non-linear relationships between variables.