Predicting perceived financial durability for cryptocurrencies by employing an integrated neural network methodology

Abstract

Cryptocurrencies have garnered widespread recognition as a groundbreaking advancement in the financial sector, holding the capacity to transform traditional financial systems by facilitating quicker, more cost-effective, and more inclusive value transfers. Understanding the potential transformation of current financial frameworks by these digital assets necessitates an examination of their sustainability, making it a critical aspect to explore. Consequently, the primary aim of the study was to identify the pivotal factors that could predict the perceived financial sustainability of cryptocurrencies, delving into the core of their long-term viability. A comprehensive framework was put forward based on the “Expectation Confirmation Theory” (ECT), which was then subjected to a detailed analytical scrutiny integrating “Structural Equation Modeling” (SEM) with methodologies drawn from “Artificial Neural Network” (ANN) to enhance the research’s depth and breadth. The research cohort consisted of 1164 individuals aged between 16 and 60 years, carefully chosen to participate in the investigation during the time period January 2024 to May 2024, ensuring a diverse and representative sample for robust analysis. The results emphasized the substantial sway of users’ expectation confirmation levels on their satisfaction. Comparatively, the outcomes from the SEM analysis were juxtaposed with the outcomes from the advanced ANN multi-layer perceptron demonstrating strong predictive performance with low RMSE values for both training and testing datasets, thus highlighting the prowess of ANN in bolstering predictive prowess within the specific research realm. The integration of SEM and ANN methodologies proved instrumental in unraveling the intricate interplay of factors influencing the sustainability and user satisfaction aspects of cryptocurrencies, paving the way for a more nuanced understanding of their implications on the financial landscape.