Multidimensional scaling (MDS) is a visualization of the distances between a set of objects, and can also be used as an unsupervised dimensionality reduction algorithm. It is a dimensionality reduction method that can alleviate the sparse sample data and difficulty in distance calculation that occur in high-dimensional situations.

It is a linear dimensionality reduction method. Unlike principal component analysis and linear dimensionality reduction analysis, the goal of multidimensional scaling is not to retain the maximum separability of the data, but to pay more attention to the internal features of the high-dimensional data. The multidimensional scaling algorithm focuses on retaining the "similarity" information in the high-dimensional space, and in the general problem solving process, this "similarity" is usually defined by Euclidean distance.