A survey report of different technique or component for dimensionality reduction in data science

To train a machine learning model using a data record which has multiple properties, is typically a difficult task. The development of over fitting of the susceptible model and the growth of model characteristics are always inversely correlated. Since not all of the traits are always significant, th...

Full description

Saved in:
Bibliographic Details
Published inI-Manager's Journal on Software Engineering Vol. 17; no. 1; p. 38
Main Authors Sangeeta, Devi, Munish, Saran, Rajan, Kumar, Upendra, Nath Tripathi
Format Journal Article
LanguageEnglish
Published Nagercoil iManager Publications 01.07.2022
Subjects
Data science
Datasets
Discriminant analysis
Eigenvectors
Feature selection
Humidity
Machine learning
Methods
Principal components analysis
Reduction
Software engineering
Online AccessGet full text

Cover

More Information
Summary:To train a machine learning model using a data record which has multiple properties, is typically a difficult task. The development of over fitting of the susceptible model and the growth of model characteristics are always inversely correlated. Since not all of the traits are always significant, this observation was made, and for instance, several attributes might merely make the data noisier. Techniques for dimensionality reduction are employed to address this issue. In this paper we have also discussed the different approaches and techniques of dimensionality reduction techniques.
ISSN:0973-5151
2230-7168
DOI:10.26634/jse.17.1.19087