Saved in:
Bibliographic Details
Main Authors: Daugulis, Peteris, Vagale, Vija, Mancini, Emiliano, Castiglione, Filippo
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.09246
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911202418884608
author Daugulis, Peteris
Vagale, Vija
Mancini, Emiliano
Castiglione, Filippo
author_facet Daugulis, Peteris
Vagale, Vija
Mancini, Emiliano
Castiglione, Filippo
contents The problem of choosing appropriate values for missing data is often encountered in the data science. We describe a novel method containing both traditional mathematics and machine learning elements for prediction (imputation) of missing data. This method is based on the notion of distance between shifted linear subspaces representing the existing data and candidate sets. The existing data set is represented by the subspace spanned by its first principal components. Solutions for the case of the Euclidean metric are given.
format Preprint
id arxiv_https___arxiv_org_abs_2510_09246
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A PCA-based Data Prediction Method
Daugulis, Peteris
Vagale, Vija
Mancini, Emiliano
Castiglione, Filippo
Machine Learning
The problem of choosing appropriate values for missing data is often encountered in the data science. We describe a novel method containing both traditional mathematics and machine learning elements for prediction (imputation) of missing data. This method is based on the notion of distance between shifted linear subspaces representing the existing data and candidate sets. The existing data set is represented by the subspace spanned by its first principal components. Solutions for the case of the Euclidean metric are given.
title A PCA-based Data Prediction Method
topic Machine Learning
url https://arxiv.org/abs/2510.09246