Purpose: This research examines and contributes to the behavioural lit­erature on voluntary tax compliance. It focuses on the use and potential of machine-learning (ML) methods and models to predict individual tax morale across Europe, and it identifies the factors that influence predic­tive accuracy.Design/Methodology/Approach: Using data from the fifth wave (2017– 2020) of the European Values Survey (EVS), a data-driven, systematic approach employing six ML methods is applied to predict individual tax morale across Europe. The importance of formal, informal and socio-de­mographic factors is assessed, and the study tests whether incorporating the Corruption Perception Index (CPI) improves predictive accuracy.Findings: The results indicate that ML methods and models can enhance understanding and prediction of individual tax morale in Europe. Among the deployed models, artificial neural networks (ANNs) achieved the highest accuracy. Accuracy increased across all ML methods when the CPI was included. Attitudes towards bribery, perceptions of immigrants’ im­pact on the national welfare system, and gender emerged as significant formal, informal and socio-demographic factors.Academic contribution to the field: The study offers a novel application of data-driven ML methods to the prediction of individual tax morale. Given the scarcity of empirical ML research in the social sciences, the find­ings provide valuable insights in a European context and may serve as a basis for further global research.Practical Implications: The conclusions are particularly relevant for gov­ernments and tax administrations seeking to improve tax compliance and revenue collection. In the European context, the results confirm the virtu­ous circle linking effective government performance, high tax morale and voluntary tax compliance—insights that are crucial for decision-makers, regulators, European institutions and tax-policy makers.Originality/Value: The findings confirm that, when ML methods are ap­plied, individual tax morale can be viewed as an outcome of interactions between formal and informal institutions. They also show that predictive accuracy is higher in countries with lower corruption, as indicated by a higher CPI.    

The paper is concerned with hexacyclic systems (Fn) and their M¨obius counterparts (Mn). Continuing the studies in MATCH Commun. Math. Comput. Chem. 94 (2025) 477, the characteristic polynomial and the eigenvalues of the Sombor matrix of Fn and Mn, and the respective Sombor energies are determined. Upper and lower bounds for the Sombor energy in terms of the number of hexagons are also obtained.

The hexacyclic system graph Fn is the graph derived from a linear hexagonal chain Ln with n > 1 hexagons by identifying two pairs of ends of Ln. The M¨obious hexacyclic system graph Mn is the graph derived from a linear hexagonal chain Ln with n > 1 hexagons by identifying two pairs of ends of Ln with a twist. In this paper, we compute, in a closed form, the resolvent energy, the Laplacian and the signless Laplacian resolvent energy, as well as the resolvent Estrada index and the resolvent signless Estrada index of Fn and Mn. All five indices are expressed as a rational function in the number n of hexagons, defined in terms of Chebyshev polynomials of the first and the second kind. Those expressions allow for a fast numerical computation of indices and for deducing sharp bounds on their growth.

In this paper we derive some new identities involving the Fibonacci and Lucas polynomials and the Chebyshev polynomials of the first and the second kind. Our starting point is a finite trigonometric sum which equals the resolvent kernel on the discrete circle with $m$ vertices and which can be evaluated in two different ways. An expression for this sum in terms of the Chebyshev polynomials was deduced in \cite{JKS} and the expression in terms of the Fibonacci and Lucas polynomials is deduced in this paper. As a consequence, we establish some further identities involving trigonometric sums and Fibonacci, Lucas, Pell and Pell-Lucas polynomials and numbers, thus providing a"physical"interpretation for those identities. Moreover, the finite trigonometric sum of the type considered in this paper can be related to the effective resistance between any two vertices of the $N$-cycle graph with four nearest neighbors $C_{N}(1,2)$. This yields further identities involving Fibonacci numbers.

. We obtain a meromorphic continuation of the generalized Tribonacci zeta function to the whole complex plane. The residues of the generalized Tribonacci zeta functions associated to the third-order Jacobsthal, Tribonacci and Narayana sequence at negative inte-ger poles are computed.