Regression
Metadata
Regression Regression Tasks

Linear Models generate a formula to find a best-fit line through a set of data points to predict unknown values.

Types of regressions:https://camo.githubusercontent.com/726827fb52510a97169b84b5a2a45bbb0dc06510d0cb13cc7d4c81f6d3794a35/68747470733a2f2f6d69726f2e6d656469756d2e636f6d2f6d61782f323030312f312a6453466e2d754959446844666461473547586c4233412e706e67
Attributes of regression models:

  • Number of independent variables
    • Univariate: 1 feature or independent variables
    • Bivariate: 2 features or independent variables
    • Multivariate: more than 2 feature or independent variables
  • Shape of the regression
  • Type of dependent variables

Notes:

  • Regression models are based on mathematical Regression Mathematics topic.
  • Random Forest can be utilized in regression tasks. Then the mean or average prediction of the individual trees is returned.
  • They can only be used to solve regression-based problems where a relationship between the dependent and independent variables must exist.
  • Regression models are highly interpretable and fast to train.
  • Regression is not robust in handling outliers and is also prone to overfitting. to address Overfitting in linear regression, Regularization (Technique) is used.
  • Based on degree of independent variable they are divided into:
  • MSE and MAE Loss Functions are used for regression tasks
  • Binary Crossentropy and categorical Crossentropy are used as Loss Functions for classification tasks using Logistic Regression