Modeling Influenced Criteria in Classifiers' Imbalanced Challenges Based on TrSS Bolstered by The Vague Nature of Neutrosophic Theory

Abstract

Because of the advancements in technology, classification learning has become an 
essential activity in today's environment. Unfortunately, through the classification process, we 
noticed that the classifiers are unable to deal with the imbalanced data, which indicates there are 
many more instances (majority instances) in one class than in another. Identifying an appropriate 
classifier among the various candidates is a time-consuming and complex effort. Improper selection 
can hinder the classification model's ability to provide the right outcomes. Also, this operation 
requires preference among a set of alternatives by a set of criteria. Hence, multi-criteria decision
making (MCDM) methodology is the appropriate methodology can deploy in this problem. 
Accordingly, we applied MCDM and supported it through harnessing neurotrophic theory as 
motivators in uncertainty circumstances. Single value Neutrosophic sets (SVNSs) are applied as 
branch of Neutrosophic theory  for evaluating  and ranks classifiers and allows experts to select the 
best classifier So, to select the best classifier (alternative), we use MCDM method called Multi
Attributive Ideal-Real Comparative Analysis (MAIRAC) and the criteria weight calculation method 
called Stepwise Weight Assessment Ratio Analysis (SWARA) where these methods consider single
value neutrosophic sets (SVNSs) to improve and boost these techniques in uncertain scenarios. All 
these methods are applied after modeling criteria and its sub-criteria through a novel technique is 
Tree Soft Sets (TrSS). Ultimately, the findings of leveraging these techniques indicated that the hybrid 
multi-criteria meta-learner (HML)-based classifier is the best classifier compared to the other 
compared models.

DOI: 10.5281/zenodo.10858939