Article

October 02, 2026

Spatial Relations between ICMS Quota Share Repasses and Municipal Economic Activity in Goiás

Spatial Relations between ICMS Quota Repasses and Municipal Economic Activity in Goiás

Érika Martins Lima Cherubino; João Ítalo Bolqui Dutra

DOI: 10.22167/2675-6528-202602880

Article derived from a Course Conclusion Work (TCC), with content based on the student’s original work and adapted to the editorial format of the E&S Magazine with the support of the ResumeAI tool, an artificial intelligence solution developed by Instituto Pecege for textual synthesis and organization.

Summary

A quantitative research applied to state tax administration was conducted with the objective of spatially analyzing the per capita values of the municipal share of the Tax on Circulation of Goods and Services (ICMS) and verifying its relationship with the per capita Gross Domestic Product (GDP) of the municipalities in Goiás in the period from 2014 to 2023. For this purpose, techniques of Exploratory Spatial Data Analysis were employed, including choropleth maps, Global and Local Moran’s I (LISA), Getis-Ord Gi* statistics, and SKATER spatial clusters. The results demonstrated that the territory of Goiás was organized in a heterogeneous and non-random manner, characterized by persistent regional inequalities that reproduced over time and maintained a relatively stable territorial configuration. It was observed that the state’s fiscal geography was influenced by economic geography in the analyzed period, but this relationship did not always prove to be linear in space, being marked by territorial, fiscal, and regional specificities. It was concluded that the study provides relevant elements for understanding the dynamics of revenue collection and for the strategic action of the state tax administration, especially in improving regional revenue collection, incentive, and enforcement policies.

Keywords: Spatial Analysis; Tax Collection; State of Goiás; Gross Domestic Product.

1. Introduction

Taxes represent the core of revenue collection for federative entities in Brazil. At the state level, the Tax on the Circulation of Goods and Services (ICMS) is the state-competent tax that applies to the circulation of goods and the provision of interstate, intermunicipal, and communication transport services. A portion of ICMS revenue is shared with municipalities, constituting one of their main sources of income, as highlighted by Gremaud et al. (2024).

From an economic point of view, ICMS is classified as a value-added tax, whose rate applies to the value added to the good at each stage of the production chain. This means that the amount to be collected depends directly on the tax base on which it is levied. In this context, the volume of tax collection is influenced by the level of economic activity and income, with economic growth driving an increase in collection and economic slowdown resulting in the opposite effect (Gremaud et al., 2024).

Spatial Analysis emerges as a fundamental tool for understanding complex phenomena, given the interrelationship between geographically close elements, according to the first law of Geography formalized by Tobler (1970). This approach allows associating collected data with geographic variables, contributing to the organization and understanding of various socio-spatial aspects (Cardoso et al., 2020). Previous studies have already applied spatial autocorrelation to fiscal transfers and municipal economic performance, such as the Ecological ICMS in Minas Gerais (Sgarbi et al., 2018) and the economic performance of municipalities in Santa Catarina (Begnini et al., 2024).

However, no studies were identified that spatially relate the ICMS quota and the Gross Domestic Product (GDP) per capita in the municipalities of Goiás, giving an unprecedented character to this research in this territorial scope. Understanding the regional dynamics of revenue collection and the strategic action of state tax administration are crucial for improving regional policies for revenue collection, incentives, and oversight, justifying the relevance of this study.

Given the above, the present study aims to spatially analyze the per capita values of the municipal share of ICMS and verify its relationship with the per capita Gross Domestic Product (GDP) of municipalities in Goiás from 2014 to 2023. The motivation for conducting this study is to provide relevant elements for understanding the regional dynamics of tax collection and for the strategic action of state tax administration, especially in improving regional tax collection, incentive, and enforcement policies.

2. Material and Methods

This study was characterized as a quantitative research, applied to state tax administration, with an exploratory and analytical approach. The objective was to spatially analyze the per capita values of the municipal share of the Tax on Circulation of Goods and Services (ICMS) and verify its relationship with the per capita Gross Domestic Product (GDP) of the municipalities in Goiás. The investigation covered the period from 2014 to 2023, focusing on the identification of spatial patterns and relationships.

The unit of analysis comprised the 246 municipalities of the state of Goiás, located in the Center-West region of Brazil. Data regarding the municipal quota share transfers of ICMS were extracted from the Goiás Open Data Portal. Additionally, data on the Gross Domestic Product (GDP) of the municipalities, for the same period, were obtained from the Brazilian Institute of Geography and Statistics (IBGE, 2024).

The analysis time window was set from 2014 to 2023. After collection, the data underwent cleaning, standardization, and organization steps, including handling invalid or missing values, name normalization, and annual tabular consolidation. For spatial analyses, georeferencing data of the municipal perimeters of Goiás were obtained in GeoJSON format.

To mitigate scale effects and allow for comparative analyses, data normalization by population was performed, converting the raw values of ICMS and GDP to per capita values. The resident population of each municipality was used for both calculations (Vianna and Costa, 2025). An additional step involved applying the natural logarithm to the per capita values of ICMS and GDP, due to the asymmetries observed in their distributions (Wooldridge, 2007).

The data analysis began with Exploratory Data Analysis (EDA) techniques, applying summary measures such as mean, median, and mode to describe the dispersions and distribution shapes of the values (Fávero and Belfiore, 2024). Subsequently, to investigate spatial patterns and relationships, Exploratory Spatial Data Analysis (ESDA) was employed, which integrates location information as a constitutive part of the phenomenon (Anselin, 2023), aiming to identify patterns of associations and groupings of similar values (Hao, 2019).

A fundamental concept in AEDE is spatial autocorrelation, which measures the association between attribute similarity and geographic similarity, characterized by a neighborhood relationship (Druck et al., 2004). To quantify this global autocorrelation, Moran’s I Statistic was used. This index is based on the calculation of the product of deviations of values from the global mean, considering a spatial weights matrix. Statistical significance was determined by pseudo-significance tests, using permutations.

To identify spatial clusters in different locations, the Local Moran’s I (LISA) was applied, which allows the visualization of spatial autocorrelation patterns at the municipal level. Additionally, to measure the local intensity of concentration of high values (hotspots) and low values (coldspots), the Getis-Ord Gi* statistic was used (Anselin, 2023). This technique calculated z-scores for each dataset, enabling the identification of element clusters.

The spatial regionalization of municipalities, grouping them by similarity and contiguity, was performed using the “Spatial ‘K’luster Analysis by Tree Edge Removal” (SKATER) algorithm. This technique is suitable for forming spatially contiguous and internally homogeneous clusters (Assunção et al., 2006). The process involved obtaining a Minimum Spanning Tree (MST) and evaluating pruning points by calculating the Sum of Squared Deviations (SSD) for the subtrees (Anselin, 2023).

The analyses were implemented in Python language, using libraries such as Pandas for data manipulation, PySAL and ESDA for spatial analysis, GeoPandas for spatial data, and Folium for interactive map generation.

3. Results and Discussion

The initial analysis of the dynamics of the study variables revealed important characteristics in the distribution of per capita values of transfers from the Tax on Circulation of Goods and Services (ICMS) and Gross Domestic Product (GDP) in the municipalities of Goiás. A striking distributive heterogeneity was observed, with arrangements indicating positive asymmetries. This means that the majority of municipalities were concentrated in intermediate value ranges, while a few presented relatively high values. The asymmetry was more pronounced for per capita GDP, suggesting a more significant influence of municipalities with high economic activity on the state’s overall average.

Despite the application of the logarithmic transformation to mitigate scale effects, the asymmetry in the distribution of monetary values remained visible throughout the entire period from 2014 to 2023. This persistent pattern, even with the nominal growth in per capita collection and GDP values, indicates that heterogeneity among municipalities did not dissolve but rather reproduced itself over the decade. Such a finding points to the existence of persistent and structural fiscal and economic disparities in the Goiano territory, reflecting a non-random spatial organization.

When examining the municipalities with the highest and lowest values of ICMS per capita and GDP per capita in 2023, it was found that Perolândia, Davinópolis, Chapadão do Céu, Paraúna, Barro Alto, and Turvelândia were among the top six in both variables. These municipalities are characterized by economies strongly based on agriculture and industry, as pointed out by Vianna and Costa (2025). A notable distinction was the municipality of Alto Horizonte, which, despite not being among the top ten in GDP per capita, registered the highest value of ICMS transfer per capita in Goiás, indicating specificities in the relationship between economic activity and tax collection in certain local contexts.

The Gini coefficients calculated for the study variables, in the period from 2014 to 2023, indicated moderate inequalities in their distributions. Comparatively, the inequality in the distribution of per capita ICMS was higher and more persistent than that observed for per capita GDP. While the Gini coefficient for per capita ICMS remained predominantly in the range of 0.35 to 0.37, per capita GDP showed greater fluctuation, varying between 0.29 and 0.33 over the time series. This difference suggests that, although both variables demonstrate inequality, the distribution of the ICMS share is more rigidly structured in terms of disparity.

The transition to exploratory spatial data analysis allowed for the visualization of territorial patterns. Through choropleth maps, it was observed that both per capita ICMS transfers and per capita GDP showed areas of higher relative intensity in the southern, southwestern, and parts of the southeastern regions of the state. Additionally, isolated dark clusters were identified in the north and north-central areas. In contrast, the central and east-central regions, especially around the Federal District, exhibited lower intensity for both variables, outlining a heterogeneous fiscal and economic geography.

A visual comparison of the maps revealed a partial convergence in the patterns observed for the two variables, suggesting a territorial coincidence between higher levels of economic activity and greater per capita ICMS transfers. However, per capita GDP showed a less fragmented spatial configuration, presenting greater continuity and regional cohesion compared to per capita ICMS. Territorial disparities were recurrent throughout the period, reinforcing the hypothesis that the differentials in ICMS and per capita GDP transfers are persistent and structural, not merely conjunctural.

The existence of positive and statistically significant spatial autocorrelation was confirmed by the results of the Global Moran’s I for both variables in all analyzed years. For per capita ICMS transfers, the Global Moran’s I values ranged from 0.299683 in 2014 to 0.361403 in 2018, while for per capita GDP, the values oscillated between 0.361337 in 2020 and 0.412044 in 2023. In all cases, the p-value was 0.001, strongly rejecting the null hypothesis of spatial randomness. This indicates that municipalities with high per capita ICMS values tend to be close to others with high values, and the same applies to municipalities with low values, evidencing a non-random spatial organization.

The analysis of the Global Moran’s I also revealed that GDP per capita presented systematically higher and more stable values throughout the historical series compared to ICMS per capita. This finding suggests that the spatial autocorrelation of GDP is more intense and robust, indicating greater stability in economic clustering patterns compared to tax collection patterns. The persistence of these patterns over time reinforces the idea that regional economic structures are more consolidated and less susceptible to short-term fluctuations than fiscal ones.

The Local Moran/LISA maps detailed the geography of spatial autocorrelation, identifying well-defined and recurrent local territorial cores. For per capita ICMS transfers, two persistent “high-high” clusters were observed: a larger one in the southwest region and another of smaller proportions in the southeast region of the state. The recurrent “low-low” clusters were located in the central-eastern portion, with a strong association to the surroundings of the Federal District. These patterns indicate the formation of high and low revenue clusters that remained stable throughout the analyzed period.

For GDP per capita, the Local Moran/LISA maps exhibited a more continuous, extensive, and stable configuration, especially in the large “high-high” clusters of the south and southwest regions, and in the “low-low” clusters of the northeast region. This greater stability and extent of GDP per capita clusters are consistent with the higher values of Global Moran’s I observed for this variable. The presence of such clusters suggests that economic activity is organized in more cohesive and less fragmented territorial blocks than ICMS collection.

The application of the Getis-Ord Gi* statistic to identify “hotspots” (high concentrations) and “coldspots” (low concentrations) complemented the analysis. For per capita ICMS transfers, the main “hotspot” was located in the southwest-south portion of the state, remaining visible in all years. A smaller, but persistent, “hotspot” was observed in the southeast. The “coldspots” were mainly organized in the central-east region, with a strong visual association to the surroundings of the Federal District, and in smaller patches in parts of the north, northeast, and central areas, whose visibility varied between years.

The Getis-Ord Gi* maps of per capita GDP revealed a more extensive and stable “hotspot” in the southwest-south portion of the state, visible in all years of the analysis, and another equally persistent “hotspot” in the southeast. The “coldspots” were mainly concentrated in the northern and northeastern regions of the state, exhibiting strong spatial continuity throughout almost the entire series. In addition to these, cold patches were observed in central areas in several years. In comparative terms, per capita GDP presented more extensive, continuous, and spatially robust “hotspot” and “coldspot” regions than per capita ICMS, reinforcing the idea of greater economic cohesion.

The regional economic context corroborates the observed spatial patterns. Southwestern Goiás, with municipalities such as Jataí and Rio Verde, stood out as a region of extensive “high-high” clusters and “hotspots” for ICMS and GDP. Romanatto et al. (2011) and the Secretariat of State for Management and Planning of Goiás (2012) emphasize that Rio Verde, one of the largest grain producers, developed an “agricluster” with industrial expansion and growth in the services sector, positively impacting ICMS collection and GDP. Jataí, in turn, is a leading example of national agribusiness with large processing industries.

The southeastern region of the state, with emphasis on Catalão, also presented clusters of high values and “hotspots”, driven by significant industrial growth indicators in recent decades. The attraction of large companies in the mining and assembly of vehicles and agricultural machinery sectors was influenced by the strategic location and mineral wealth of the municipality (Romanatto et al., 2011). These economic factors explain the formation and persistence of clusters of high revenue and economic activity in these regions.

In contrast, the “coldspots” and “low-low” clusters were predominantly located in the central, east-central, northern, and northeastern regions of the state. These areas are characterized by lower economic dynamism and lower industrial density, with a negative highlight for the surroundings of the Federal District, where cities exhibit low development of industrial and agricultural activities (Romanatto et al., 2011). The persistence of these spatial patterns over time suggests that the observed clusters are strongly influenced by structural economic and territorial processes.

The clustering of municipalities using the SKATER technique added a complementary dimension to the analysis, regionalizing the state of Goiás into contiguous sets of municipalities with internally more homogeneous characteristics of ICMS and GDP. For per capita ICMS transfers in 2023, the spatial regionalization was marked by relatively large groupings in the southwest, northeast, and northwest, in addition to the surroundings of the Federal District and parts of the south and southeast. The presence of smaller and more fragmented regions in the central area of the state suggests that, in this portion of the territory, per capita ICMS values varied more abruptly between neighboring municipalities, hindering the formation of large homogeneous blocks.

For GDP per capita, the 2014 and 2023 SKATER maps revealed a more continuous and regionally consolidated spatial configuration, with large contiguous blocks well-defined in the northern, southeastern, and southwestern regions of the state. The behavior of SKATER “clusters” over the analysis period suggests spatial persistence and greater territorial robustness of GDP per capita, with relatively homogeneous macro-regions and less fragmentation than observed in ICMS per capita. This difference in cluster robustness reinforces the idea that economic geography has a more stable and cohesive structure than fiscal geography.

In summary, the research results demonstrated that the Goiano territory organized itself in a heterogeneous and non-random manner, characterized by persistent regional inequalities that were reproduced over time and maintained a relatively stable territorial configuration. The state’s fiscal geography was influenced by economic geography in the analyzed period, but this relationship did not always prove to be linear in space, being marked by territorial, fiscal, and regional specificities. Per capita ICMS showed greater fragmentation and less stability in its spatial patterns, while per capita GDP exhibited a more continuous, robust, and stable pattern, with more extensive territorial clusters and greater intensity in global and local autocorrelations.

4. Conclusion

This study sought to spatially analyze the per capita values of the municipal share of the Tax on Circulation of Goods and Services (ICMS) and verify its relationship with the per capita Gross Domestic Product (GDP) of the municipalities of Goiás between 2014 and 2023. It was found that the territory of Goiás was organized in a heterogeneous and non-random manner, characterized by persistent regional inequalities that reproduced over time, maintaining a relatively stable territorial configuration. It was observed that the state’s fiscal geography was influenced by economic geography in the analyzed period, although this relationship did not always prove to be linear in space, being marked by territorial and fiscal specificities. It was identified that the per capita ICMS showed greater fragmentation and less stability in its spatial patterns, while the per capita GDP exhibited a more continuous, robust, and stable pattern, with larger territorial clusters and greater intensity in global and local autocorrelations, with “hotspots” in the southwest-south and southeast, and “coldspots” in the central, east-central, north, and northeast regions.

The main contribution of this study lies in providing relevant elements for understanding the regional dynamics of tax collection and for the strategic action of state tax administration. The findings indicate the need to improve regional tax collection policies, incentives, and oversight, considering the regionalized logic of tax distribution and the spatial evidence of inequalities. The persistence of regions with distinct fiscal profiles suggests that tax collection and its territorial distribution should be understood in light of an approach that values local specificities, allowing for interventions more aligned with the reality of the municipalities of Goiás.

Bibliographic References

Anselin, L. 2023. An Introduction to Spatial Data Science with GeoDa – Volume 1: Exploring Spatial Data. Center for Spatial Data Science – University of Chicago, Illinois, Estados Unidos. Disponível em: <https://lanselin.github.io/introbook_vol1>. Acesso em: 15 jan. 2026.

Assunção, R. M.; Neves, M.C.; Câmara, G.; Freitas, C. da C. 2006. Efficient regionalization techniques for socio-economic geographical units using minimum spanning trees. International Journal of Geographical Information Science, 20(7): 797–811. Disponível em: < http://www.dpi.inpe.br/gilberto/papers/assuncao_neves_camara_ijgis.pdf>. Acessado em 10 jan. 2026.

Begnini, S.; Carvalho, C.E.; Rossetto, C.R. 2024. Autocorrelação espacial: desempenho econômico dos municípios catarinenses entre 2012-2020. Interações 25(3): e2533910.

Cardoso, P.V.; Silva, V.; Bastos, I.B.; Costa, E.C.P. 2020. A importância da análise espacial para tomada de decisão: um olhar sobre a pandemia de COVID-19. Revista Tamoios, 16(1): 125-137. Disponível em: <https://www.e-publicacoes.uerj.br/tamoios/article/view/50440>. Acesso em: 30 set. 2025.

Druck, S.; Carvalho, M.S.; Câmara, G.; Monteiro, A.V.M. 2004. Análise Espacial de Dados Geográficos. Empresa Brasileira de Pesquisa Agropecuária [EMBRAPA], Brasília, DF, Brasil. Disponível em: <http://www.dpi.inpe.br/gilberto/livro/analise/>. Acesso em: 30 set. 2025.

Fávero, L.P.; Belfiore, P. 2024. Manual de Análise de Dados. 2ed. LTC, Rio de Janeiro, RJ, Brasil.

Gremaud, A.P.; Vasconcellos, M.A.S.; Jr., R.T.; Naruhikos, S. 2024. Economia Brasileira Contemporânea. 9ed., Atlas, Rio de Janeiro, RJ, Brasil. Disponível em: <https://app.minhabiblioteca.com.br/reader/books/9786559776450/>. Acesso em: 06 out. 2025.

Hao, P. 2019. Spatial analysis. In: Orum, A. (ed.). Wiley Blackwell Encyclopedia of Urban and Regional Studies. Wiley-Blackwell, Hong Kong. Disponível em: <https://www.researchgate.net/publication/332425310_Spatial_Analysis>. Acesso em: 13 out. 2025.

Instituto Brasileiro de Geografia e Estatística [IBGE]. 2024. Nota técnica 02/2024 – PIB dos municípios. Disponível em: < https://biblioteca.ibge.gov.br/visualizacao/livros/liv102094.pdf>. Acesso em: 17 out. 2025.

Romanatto, E.; Arriel, M.F.; Silva, G.J.C.D. 2011. Aglomeração, caracterização e dinâmica econômica setorial dos municípios do Estado de Goiás em 2008: Avaliação empírica e proposição de política. Goiânia, Goiás, Brasil. Disponível em: <https://www.ipea.gov.br/code2011/chamada2011/pdf/area7/area7-artigo46.pdf>. Acesso em: 15 fev. 2026.

Secretaria de Estado de Gestão e Planejamento de Goiás. 2012. Perfil e potencialidades dos municípios goianos. Disponível em: <https://goias.gov.br/imb/wp-content/uploads/sites/29/2024/02/repositorio_2012_017_outras_publicacoes_perfil_e_potencialidades_dos_municipios_goianos.pdf>. Acesso em: 15 fev. 2026.

Sgarbi, L.A.; Gonçalves, R.M.L.; Abrantes, L.A.; Brunozi Jr., A.C. 2018. Análise espacial do ICMS Ecológico e suas relações com o desenvolvimento socioeconômico dos municípios mineiros. Reuna 23(4): 15-41.

Tobler, W.R. 1970. A computer movie simulating urban growth in the Detroit region. Economic Geography, 46(2): 234-240. Disponível em: <https://www.jstor.org/stable/143141>. Acesso em: 13 out. 2025.

Vianna, P.J.B.; Costa, R. C. 2025. Produto interno bruto dos municípios goianos – 2023. Disponível em: <https://goias.gov.br/imb/wp-content/uploads/sites/29/2025/11/boletim_046_2025_PIB_regional_consolidado_2023.pdf>. Acesso em: 21 jan. 2026.

Wooldridge, Jeffrey M., 2007. Introdução à Econometria: Uma Abordagem Moderna. 4ed. Thomson Learning. São Paulo, SP, Brasil.

Article originating from the Final Course Project of the Specialization in Data Science and Analytics of the MBA USP/Esalq

To learn more about the course, click here and access the MBX Academy platform

You may also like

Economy, Investments And Banking

October 23, 2026

Financial Education, Behaviors and Biases in Financial Decision Making

Personal financial management represents a growing challenge, influenced by cognitive biases that affect decision-making, even in individuals with high knowledge. The present study analyzed the relationship between the level of financial education and the occurrence of behavioral biases in the financial decision-making of adults residing in Brazil. An applied, quantitative, and descriptive-correlational field survey was conducted by administering a structured questionnaire to 163 respondents. The instrument included sociodemographic variables, financial knowledge and habits, and hypothetical situations to identify cognitive biases. The results indicated that higher levels of financial education were associated with better financial control, saving, and investment practices, with significant correlations with income and schooling. However, the presence of behavioral biases (anchoring, loss aversion, scarcity, optimism/negativity, present bias, status quo, overconfidence, and mental accounting) persisted even among individuals with higher schooling and income, with no statistically significant association with the analyzed sociodemographic variables. It was concluded that financial education, although essential for financial organization and control, was not sufficient to neutralize the influence of cognitive biases. The incorporation of behavioral approaches into financial education programs is suggested.

Keywords: Financial behavior; Behavioral economics; Personal finance; Cognitive heuristics; Cognitive biases.

October 22, 2026

Consumer Journey in the Decision to Purchase Infoproducts in the Digital Environment

The expansion of e-commerce and technological transformation have driven the need to understand consumer behavior regarding infoproducts, whose perceived experience has become crucial for professional development. The study aimed to analyze the factors that influenced the purchase decision of infoproducts in the digital environment, considering the stages of the consumer journey. An applied, quantitative, and descriptive research was conducted through a field survey with 100 consumers from Serra Gaúcha. Data collection occurred via a structured questionnaire, using non-probabilistic sampling. The results revealed a qualified audience with strong “mobile-first” behavior. It was found that the availability of detailed information and social approval were the main attraction triggers in the pre-purchase phase. In the transactional and subsequent stages, the minimization of operational friction, the agility of immediate access, and system security proved crucial for conversion and satisfaction, although gaps in human support efficiency were identified. Retention was based on the trust generated by positive past experiences, overcoming the price factor. It was concluded that the infoproduct consumer journey operates as an integrated system, requiring alignment between technological infrastructure, content curation, and support humanization to ensure engagement.

Keywords: E-commerce; Consumer behavior; Consumer experience; Loyalty; Virtual business.

October 22, 2026

Forecast of Aggregate Default in the Brazilian Financial System by Sarimax Model with Macroeconomic Variables

Aggregate non-payment in the Brazilian financial system is a crucial indicator of credit risk, the prediction of which is regulated by CMN Resolutions n.° 4.557/2017 and 4.966/2021 for the prospective measurement of expected losses. Aggregate non-payment was modeled and predicted using the SARIMAX model, projecting its trajectory until December 2026 under optimistic, base, and pessimistic scenarios. 164 monthly observations (July/2012 to February/2026) and macroeconomic variables such as unemployment, Selic, IPCA, IBC-Br, and household debt were used. The specification with contemporaneous variables was selected based on information criteria and coefficient stability, and residual diagnostics confirmed statistical adequacy, with a MAPE of 3.12%. Historical non-payment ranged between 4.33% and 7.64%. The estimation identified unemployment (β = 0.2534; p < 0.001) and Selic (β = 0.2128; p < 0.001) as the main positive determinants, with strong temporal persistence (AR(1) = 0.8965). Selic showed increasing correlation with non-payment (r = 0.62 at lag 12), while unemployment demonstrated a contemporaneous effect (r = 0.33). Projections indicated non-payment between 6.30% and 7.98% in December 2026, with a range of 1.68 percentage points, highlighting direct implications for provisioning in financial institutions.

Keywords: Unemployment; Predictive modeling; Monetary policy; Loss provisioning; Time series.