Effective Data Classification using Interval Neutrosophic Covering Rough Sets based on Neighborhoods for FinTech Applications

• DOI: 10.54216/ijns.250319
• Publication Date: 2024-10-30T18:19:02Z
• Authors: Maksim Maksim; ; ; ; ; Irina Kosorukova; Veronika Denisovich; Elena Klochko; Alexey Dengaev
• Keywords: Interval data

Neutrosophic set (NS) is particularly appropriate in applications where data incomplete, unclear, or inconsistent, which offers an effectual means for analyzing and exhibiting complex mechanisms. An NS a mathematical technique to manage uncertainty, indeterminacy, imprecision. It enlarges classical sets, IF fuzzy sets by presenting three degrees such as indeterminacy (I), false (F), truth (T). Financial technology (Fintech) plays essential part advancing modern society, technology, economies, various fields. crisis prediction (FCP) crucial role shaping economic outcomes. Past research has predominantly focused on using deep learning (DL), machine (ML), statistical methods forecast the financial stability of business. In this manuscript, we focus development Effective Data Classification Interval Covering Rough Sets based Neighborhoods Multi-Strategy Improved Butterfly Optimization (EDCINCRS-MSIBO) Algorithm FinTech Applications. contains distinct kinds stages normalization, feature selection, classification, parameter tuning. EDCINCRS-MSIBO technique, min-max normalization-based pre-processing model scale raw into uniform format. For subset whale optimizer algorithm (WOA) employed reduce dimensionality improve efficiency selecting most relevant features. addition, takes place interval neutrosophic covering rough (INCRS) classifier utilized detection classification crisis. Finally, multi-strategy improved butterfly optimization (MSIBOA) exploited optimum adjustment INCRS model. To confirm better predictive solution model, wide range simulations are executed two benchmark databases. The comparative result analysis displays encouraging outcomes method existing techniques