Data Science Articles

Dimensionality reduction is the process of reducing the number of random variables under consideration by obtaining a set of principal variables. It can be divided into feature selection and feature extraction.

• Principal Component Analysis (PCA): Reduces the dimensionality of the data by selecting the most important features that capture maximum information.
• Principal Component Regression (PCR): PCR is a regression technique that is based on PCA. It’s used for building predictive models with high-dimensional data.
• Partial Least Squares Regression (PLSR): PLSR is a technique that combines features to reduce dimensionality.
• Sammon Mapping: Reduces dimensionality while preserving the structure of inter-point distances in high-dimensional space.
• Multidimensional Scaling (MDS): Aims to place objects in N-dimensional space so that their distances are preserved.
• Projection Pursuit: Finds the most interesting projection for high-dimensional data.
• Linear Discriminant Analysis (LDA): Used to find a linear combination of features that characterizes or separates two or more classes of objects or events.
• Mixture Discriminant Analysis (MDA): A generalization of LDA that involves a mixture of Gaussians.
• Quadratic Discriminant Analysis (QDA): A variant of LDA where each class uses its own estimate of variance.
• Flexible Discriminant Analysis (FDA): Combines features in a non-linear way to maximize class separability.
• Regularized Discriminant Analysis (RDA): Combines LDA and QDA.
• Partial Least Squares Discriminant Analysis: A variant of PLSR used in classification.