Journal article Open Access

Comprehensive Assessment of Imbalanced Data Classification

Smita Nirkhi; Shashikant Patil

Sponsor(s)
Blue Eyes Intelligence Engineering & Sciences Publication(BEIESP)

This is an attempt to address the various challenges opportunities and scope for formulating and designing new procedure in imbalanced classification problem which poses a challenge to a predictive modelling as many of AI ML n DL algorithms which are extensively used for classification are always designed from the perspective of with majority of focus on assuming equal number of examples for a class. It leads to poor efficiency and performance especially in minority class. As Minority class is always very crucial and sensitive to classification errors and also its utmost important in imbalanced classification. This chapter discusses addresses and gives novel as well as deep insights with unequal distribution of classes in training datasets. Largely real time and real world classifications are comprising imbalanced distribution so need specialized techniques for more challenging and sophisticated models with minimal errors and improved performance.

Files (593.2 kB)
Name Size
D7349049420.pdf
md5:4108227c0d9e577475c6443e98fa06db
593.2 kB Download
10
7
views
downloads
Views 10
Downloads 7
Data volume 4.2 MB
Unique views 7
Unique downloads 7

Share

Cite as