GLM for Big Data Analytics

M. Ataharul Islam () and Soma Chowdhury Biswas ()
Additional contact information
M. Ataharul Islam: University of Dhaka, ISRT
Soma Chowdhury Biswas: University of Chittagong, Department of Statistics

Chapter Chapter 12 in Generalized Linear Models and Extensions, 2025, pp 213-239 from Springer

Abstract: Abstract In recent times there is a growing need for models to handle big data problems. In machine learning techniques, there is an increasing use of GLM as a unified estimation and prediction method. There are different ways to use GLM in big data analytics. One approach is to use a regularized GLM to control for over or underfitting of the model. The traditional regression or classification techniques may result in large variance that can be controlled with regularization at the cost of larger bias. Decision trees and classification and regression trees (CART) can be combined with GLM as linear combinations to develop a more stable strategy for predictions with higher predictive accuracy. The flexibility of GLM in dealing with both discrete and continuous outcome variables under a unified framework makes it possible to employ GLM in determining optimal splits. Chapter 11 provides the necessary background to combine the machine learning techniques with GLM to improve the prediction performance.

Date: 2025
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-981-96-4726-2_12

Ordering information: This item can be ordered from
http://www.springer.com/9789819647262

DOI: 10.1007/978-981-96-4726-2_12

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().