Financial Customer Segmentation by Clustering and Unsupervised Learning

Esteves, Luciana Martins; Gioia, Henrique Raymundo

doi:10.22167/2675-6528-202602263

Article

September 15, 2026

Financial Customer Segmentation by Clustering and Unsupervised Learning

Luciana Martins Esteves; Henrique Raymundo Gioia

DOI: 10.22167/2675-6528-202602263

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

Summary

The growing availability of data in the financial sector has made the use of analytical techniques for segmentation and decision support relevant. The study aimed to apply clustering techniques to a customer base in order to identify homogeneous groups and interpret distinct profiles based on financial, behavioral, and registration variables. Methodologically, the research was classified as applied, descriptive, and quantitative, conducted as a case study with 750 records. Initially, the data were prepared, treated, and standardized. Subsequently, the K-Means algorithm was applied, testing different values of k and using internal validation metrics (WCSS, silhouette, Calinski-Harabasz, and Davies-Bouldin). A comparison with hierarchical methods and complementary statistical analysis by ANOVA was also performed. The results showed that, although the solution with two clusters presented better statistical performance in some metrics, the configuration with three groups had greater interpretive and analytical capacity. The identified clusters distinguished customers with higher financial vulnerability, an intermediate profile, and higher economic value, with relevant differences in income, indebtedness, credit utilization, investment, and emergency savings. It was concluded that clustering was effective in segmenting the analyzed base and demonstrated potential for supporting profile interpretation and data-driven decision-making.

Keywords: unsupervised learning; data science; clustering; K-Means; customer segmentation.

1. Introduction

The growing digitalization of the financial sector has significantly expanded the generation, storage, and strategic use of customer data. In the contemporary banking context, competitiveness is no longer solely dependent on the offering of standardized products but now requires greater analytical capacity to understand consumer profiles, behaviors, and specific needs.

In Brazil, this movement has been intensified by the expansion of digital channels, the maturation of Open Finance, and the growing use of artificial intelligence and predictive analytics for personalizing products and services. The Brazilian Federation of Banks (FEBRABAN, 2025) points out that personalization is driven, among other factors, by the use of data shared via Open Finance and by analyses based on artificial intelligence. The Central Bank of Brazil (BCB, 2023) highlights that the Open Finance ecosystem seeks to expand access to financial services that are more suited to each client’s profile and needs. In this scenario, the use of analytical methods capable of transforming large volumes of data into applicable knowledge has become relevant for both competitive differentiation and improving customer experience.

From a theoretical point of view, clustering occupies an important position in Data Science and data mining by allowing the identification of latent structures in unlabeled databases. Jain, Murty, and Flynn (1999) define clustering as the unsupervised classification of patterns into groups, highlighting its usefulness as an exploratory data analysis step. In the same direction, Han, Kamber, and Pei (2012) treat clustering as one of the central data mining techniques for pattern discovery, organization of complex databases, and support for knowledge generation from data.

From a broader perspective of statistical learning, Hastie, Tibshirani, and Friedman (2009), as well as James et al. (2021), situate unsupervised methods as appropriate tools when the researcher’s interest is less in predicting a response variable and more in understanding the internal structure of the data, identifying similarities, and describing profiles based on multiple observed attributes. Thus, clustering proves especially relevant when the research problem involves customer heterogeneity, behavioral diversity, and the need for evidence-based segmentation, rather than just intuitive or administrative criteria.

In the banking and financial sector, recent literature has reinforced the utility of analytical customer segmentation for personalization, retention, offer design, and commercial prioritization. Recent studies show that clustering algorithms, especially K-Means, have been employed to group customers based on financial, transactional, and behavioral attributes, allowing for the distinction of consumption patterns, risk, and economic value. In a recent work, Yan et al. (2025) demonstrated that clustering approaches applied to the banking context can support more precise marketing strategies, while Nofal (2024) showed that the combination of transactional characteristics and machine learning techniques enables the identification of higher-value customers in real banking databases.

These results dialogue with the broader applied literature, which recognizes segmentation as an instrument to convert raw data into actionable profiles, with the potential to guide more precise decisions. Despite this, the quality of segmentation depends on consistent methodological choices, such as variable selection, data standardization, definition of the number of clusters, and validation of the found solution, which requires technical rigor and theoretical justification so that the results are not interpreted as simple arbitrary groupings.

The relevance of this work stems, therefore, from two complementary aspects. On a practical level, the research responds to the growing need to segment customers more precisely in financial environments marked by competition, digitalization, and intensive personalization. On an academic level, the study contributes by applying Data Science fundamentals to a concrete segmentation problem, articulating clustering techniques with validation metrics and analytical interpretation of the formed groups. In this way, a merely descriptive or institutional reading of the phenomenon is avoided, and a methodologically sound approach is reinforced, supported by the literature on data mining, unsupervised learning, and financial applications. In this sense, the objective of this work was to apply clustering techniques to a customer base in the financial sector, in order to identify segments with homogeneous and statistically distinguishable characteristics, capable of supporting profile interpretation and supporting data-driven decisions.

2. Material and Methods

The research was classified as applied, descriptive, and quantitative. Regarding its purpose, it sought to generate knowledge with practical utility for understanding and segmenting customers based on financial and behavioral data. In relation to its objectives, it aimed to identify, analyze, and describe patterns present in the database, highlighting differences between the formed groups. From the perspective of the problem approach, it was quantitative, involving the use of numerical data, statistical metrics, and computational techniques. In terms of technical procedures, the work assumed the characteristics of a case study, developed from a specific database analyzed in depth.

The database used was composed of 750 customer records and 26 columns, including variables of a financial, behavioral, and registration nature, in addition to the generated cluster labels. It was an anonymized database, originating from the analytical environment of an institution in the financial sector operating in Brazil, without nominal identification of the organization, customers, or individualized sensitive information. The analyzed variables covered indicators of income, assets, account balance, credit limit, monthly investment, credit utilization, delinquency percentage, indebtedness rate, emergency fund, relationship duration, predominant interaction channel, and classification into previously identified segments. The choice of these variables was justified by their adherence to the research problem, requiring attributes capable of discriminating different customer profiles in terms of economic value, risk exposure, intensity of use of financial products, and relationship pattern with the institution. The final database incorporated the labels generated by the applied clustering methods, including K-Means and hierarchical approaches.

The data preparation and treatment stage aimed to ensure the quality, consistency, and suitability of the database for applying clustering techniques. Initially, an inspection was carried out to identify inconsistencies, such as duplicate records (removed) and missing values (treated according to the nature of the variable, with simple imputation or maintenance). Subsequently, variable typing adjustments were made (numeric, categorical, and temporal). Exploratory analysis was also conducted to understand the distribution of variables and identify possible outliers, which were kept when they represented real customer characteristics and removed only if they were inconsistencies or errors. Relevant categorical variables were retained for cluster interpretation. The database was structured in a format suitable for applying clustering algorithms.

The standardization of variables was performed using the z-score, a technique that transforms variables to the same scale with a mean of zero and a standard deviation of one. This procedure was applied exclusively to the numerical variables used in the modeling stage, with the objective of ensuring that all attributes contributed in a balanced way to the formation of groups, preventing variables with a larger numerical scale from exerting disproportionate influence.

The clustering stage was performed to identify homogeneous groups of customers, using the K-Means algorithm. K-Means divides a dataset into k groups, seeking greater internal similarity and external dissimilarity, measured by Euclidean distance. The process involves defining k, random selection of initial centroids, assignment of observations to the nearest centroid, and iterative recalculation of centroids until convergence. The algorithm’s objective is to minimize the sum of squared distances between points and the centroids of their respective clusters (WCSS), represented by Equation 1:

WCSS = Σ₁=1* Σ(x ∈ Ci) ||x – μ₁||²

(Eq. 1)

Where Ci represents the set of points belonging to cluster i, x represents each observation of the group, and μ¡ corresponds to the centroid of that cluster. The algorithm was applied to the previously treated and standardized database, being justified by its ability to handle moderately sized databases and multiple numerical variables.

The definition of the number of clusters (k) and the validation of the quality of the groupings were essential steps. Different values of k, ranging from 2 to 10, were tested using internal validation metrics: Within-Cluster Sum of Squares (WCSS), silhouette score, Calinski-Harabasz index, and Davies-Bouldin index. The joint analysis of these metrics indicated better statistical performance for the configuration with two clusters (k = 2). However, the adoption of three clusters (k = 3) was chosen for the final analysis, based on the greater capacity for interpretation and segmentation of customer profiles. Additionally, the inertia curve (elbow method) was analyzed, which showed a significant reduction in variability up to a certain point.

To compare the structure of the groups and evaluate the robustness of the segmentation, hierarchical clustering approaches were tested, including single linkage, complete linkage, and average linkage. To compare the generated clusters, the Adjusted Rand Index (ARI) was used, which assesses the degree of agreement between two clustering solutions. The results showed that the complete linkage and average linkage hierarchical methods exhibited high agreement with each other, while single linkage showed low stability. In comparison, K-Means produced more balanced groups in terms of observation distribution and showed moderate agreement with the more robust hierarchical approaches.

After the definition and validation of the groupings, the analysis of the cluster profiles was carried out to interpret their predominant characteristics. The analysis was conducted based on the means of the numerical variables in each cluster, considering financial, behavioral, and relationship indicators. Categorical variables, such as predominant interaction channel and segmentation classification, were also considered to enrich the interpretation. The clusters were described interpretatively, synthesizing the main traits of each group and comparing the differences that distinguish them from each other.

In order to verify if the identified clusters presented statistically significant differences, ANOVA was applied to the numerical variables considered in the study. ANOVA was applied to the main financial and behavioral variables in the database, such as monthly income, account balance, investment, credit utilization, delinquency percentage, and indebtedness rate. In addition to statistical significance (p-value), the magnitude of the effect was considered through partial eta squared (η²). The ANOVA results indicated that most of the analyzed variables presented statistically significant differences between the clusters, with p-values below the adopted significance level, and several variables presented high values of partial eta squared.

The execution of the analytical pipeline was performed with the Python programming language. For data treatment and manipulation, the Pandas and NumPy libraries were used. Exploratory data analysis and visualization, including inertia curve analysis, were conducted with the support of the Matplotlib library. For the application of clustering techniques (K-Means and hierarchical methods) and cluster validation (silhouette score, Calinski-Harabasz index, and Davies-Bouldin index), the Scikit-learn library was used. Statistical analysis, including ANOVA, was performed with the support of specialized computational statistics libraries. The development environment used was based on interactive notebooks.

3. Results and Discussion

The application of clustering techniques to the customer base evidenced the capacity to transform heterogeneous data into analytically distinct and interpretable groups, aligning with the literature on data mining and unsupervised learning. The quality of the segmentation depended on the combination of internal cohesion, separation between groups, and substantive utility of the results (Jain, 2010; Han, Kamber, and Pei, 2012; Hair et al., 2019). The discussion was organized to examine the definition of the number of clusters, the comparison between methods, the balance of the final partition, and the interpretation of the identified profiles.

The inertia curve was used to evaluate the reduction of intra-cluster variability as the number of groups increased. Figure 1 illustrates this behavior.

Figure 1. K-Means inertia curve

Source: Original research results

Figure 1 demonstrated a sharp drop in inertia between k=2 and k=4, followed by a progressively smaller reduction for higher values. This pattern, consistent with the elbow method, suggested that the greatest compaction gains occurred in the early partitions. This indicates that solutions with few clusters already capture a relevant portion of the base’s internal structure, but joint analysis with additional metrics and the interpretability of the generated segments are indispensable.

The normalized comparison of internal validation metrics, presented in Figure 2, allowed different quality criteria to be confronted for the choice of the number of clusters.

Figure 2. Normalized comparison of internal validation metrics

Source: Original research results

Figure 2 indicated that k=2 presented the best relative performance in the silhouette, Calinski-Harabasz, and Davies-Bouldin (inverted) metrics, signaling greater balance between internal cohesion and separation between groups. However, the decision was made to deepen the analysis with k=3, a methodologically defensible choice that considered the greater interpretability and segmentation capacity of customer profiles, according to literature that recommends considering the analytical and practical utility of clusters (Han, Kamber, and Pei, 2012).

To compare the structural consistency of the groupings obtained by distinct techniques, Table 1 presents the Adjusted Rand Index (ARI) values between the K-Means solutions and the hierarchical methods.

Table 1. Comparison between clustering methods by Adjusted Rand Index

Comparison	ARI	Reading
kmeans vs. hier_single	-0.000	Low
kmeans vs. hier_complete	0.452	Moderate
kmeans vs. hier_average	0.581	Moderate
hier_single vs. hier_complete	0.007	Low
hier_single versus hier_average	0.009	Low
hier_complete versus hier_average	0.886	High

Source: Original research results

Table 1 showed that the greatest convergence occurred between complete linkage and average linkage, with a high ARI, while single linkage presented low adherence to the other solutions. This result confirmed the limitation of single linkage in datasets with higher variability. K-Means, in turn, presented moderate agreement with the more robust hierarchical approaches, suggesting that the final partition preserved structural coherence without losing balance and interpretability.

The final distribution of clients in the adopted solution can be observed in Figure 3, which allows verifying whether the formed groups remained representative and operationally useful.

Figure 3. Distribution of clients by cluster in K-Means

Source: Original research results

Figure 3 showed a relatively balanced partition, with 274 clients in Cluster 0, 221 in Cluster 1, and 255 in Cluster 2. This balance is relevant from an analytical standpoint, as it reduces the risk of a residual cluster compromising the substantive interpretation of the results, ensuring sufficient critical mass to support consistent interpretations.

Figure 4 deepens the reading of the groupings by presenting the standardized profile of the clusters in the most relevant variables of the model.

Figure 4. Standardized profile of K-Means clusters

Source: Original research results

Figure 4 showed three quite distinct structures. Cluster 0 concentrated higher standardized values in credit utilization, delinquency, and indebtedness, combined with lower levels of income, wealth, investment, and emergency savings, characterizing a profile of greater financial vulnerability. Cluster 1 presented a more intermediate behavior, with shorter relationship time and generally moderate indicators, suggesting a transition segment. Cluster 2, on the other hand, brought together the highest relative levels of income, wealth, credit limit, investment, account balance, and emergency savings, in addition to lower delinquency and lower credit utilization, configuring the group with the highest economic value and lowest risk sensitivity.

To verify which attributes contributed most to the statistical separation between the groups, Figure 5 presents the main discriminant variables according to the magnitude of the partial eta squared in the ANOVA.

Figure 5. Main discriminant variables between clusters

Source: Original research results

Figure 5 demonstrated that emergency savings, monthly income, travel expenses, account balance, monthly investment, indebtedness rate, delinquency percentage, credit limit, credit utilization, and credit score were the attributes with the greatest discriminant power among the clusters. This result reinforces that the segmentation was not formed by statistical noise, but by structural differences associated with financial capacity, liquidity, consumption patterns, and credit risk. The predominance of these variables strengthens the internal validity of the solution, confirming that the groups were defined by dimensions substantively coherent with the problem studied.

Together, the results showed consistency between data preparation, modeling, validation, and interpretation of the clusters. Although internal metrics indicated a better statistical fit for k=2, the choice of k=3 revealed greater analytical discrimination power and greater practical utility, which is compatible with applied Data Science studies when the methodological decision is explicitly stated transparently. The base analysis supports that clustering was able to convert a complex financial base into useful segments for interpreting customer profiles and supporting data-driven decision-making.

The execution of the analytical pipeline was performed with the aid of the Python programming language, using libraries such as Pandas and NumPy for data handling, Matplotlib for exploratory analysis, and Scikit-learn for clustering (K-Means and hierarchical methods) and validation. Statistical analysis, including ANOVA, was also supported by specialized libraries. The interactive notebook environment facilitated the organization and reproducibility of the analyses (VanderPlas, 2016).

The analysis of the results obtained from the application of the clustering pipeline evidenced that the segmentation of the customer base was capable of identifying consistent and statistically relevant patterns, in line with the study’s objective of identifying homogeneous and interpretable groups through unsupervised learning techniques. The differences observed between the clusters were statistically significant, with variables such as monthly income, emergency savings, investment, and indebtedness rate presenting high discriminant power, which reinforces that the groupings reflect real differences in the data structure (Hair et al., 2019). The obtained segmentation not only met the analytical purpose of the research but also showed potential for practical application, by allowing the differentiation of strategies according to the profile of the identified groups.

4. Conclusion

This research sought to apply clustering techniques to a customer base in the financial sector, with the purpose of identifying homogeneous and statistically distinguishable segments, capable of supporting profile interpretation and data-driven decision-making. It was found that clustering was effective in segmenting the analyzed base, revealing three distinct customer profiles. The first group was characterized by greater financial vulnerability, with high levels of credit utilization, delinquency, and indebtedness, and lower levels of income, wealth, investment, and emergency savings. The second group presented an intermediate profile, while the third gathered customers of higher economic value, with superior indicators of income, wealth, investment, and emergency savings, and lower risk sensitivity. Statistical analysis confirmed that variables such as monthly income, emergency savings, investment, and indebtedness rate were the main discriminating attributes among the groups, reinforcing the internal validity of the segmentation. This approach demonstrated the potential of unsupervised learning techniques to transform complex data into structured knowledge, offering a relevant practical contribution to the differentiation of strategies and decision-making in the financial sector.

However, some limitations of the study should be acknowledged. The analysis was performed based on a single database and a specific selection of variables, which restricts the generalization of the results to other contexts or populations. Although the solution with three clusters was adopted for its greater interpretive utility, internal metrics indicated better statistical performance for a configuration with two groups, suggesting that the final choice involved a criterion of analytical utility. For future studies, it is suggested to expand the analytical base with new variables, such as indicators of transactional behavior and digital relationship, in order to deepen the discriminant capacity of the models. It is also recommended to test other clustering approaches, such as DBSCAN or Gaussian Mixture Models, and explore the integration between clustering and supervised models for risk or purchase propensity prediction, expanding the applicability of Data Science in financial environments.

Bibliographic References

Banco Central do Brasil [BCB]. (2023). Open Finance no Brasil. https://www.bcb.gov.br/estabilidadefinanceira/openfinance

Federação Brasileira de Bancos [FEBRABRAN]. (2025). Pesquisa Febraban de Tecnologia Bancária 2025. https://cmsarquivos.febraban.org.br

Han, J., Kamber, M., & Pei, J. (2012). Data mining: Concepts and techniques (3rd ed.). Morgan Kaufmann.

Hastie, T., Tibshirani, R., & Friedman, J. (2009). The elements of statistical learning: Data mining, inference, and prediction (2nd ed.). Springer.

Jain, A. K., Murty, M. N., & Flynn, P. J. (1999). Data clustering: A review. ACM Computing Surveys, 31(3), 264-323.

James, G., Witten, D., Hastie, T., & Tibshirani, R. (2021). An introduction to statistical learning: With applications in Python (2nd ed.). Springer.

Nofal, S. (2024). Identifying highly-valued

Yan, X., Li, Y., Nie, F., & Li, R. (2025). Bank customer segmentation and marketing strategies based on improved DBSCAN algorithm. Applied Sciences, 15(6), 3138.

Article originating from the Course Conclusion Work 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

Most recent

October 22, 2026

Challenges and Possibilities of the First School Year of Children with ASD for Teaching Work

October 22, 2026

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

October 22, 2026

Psychosocial Risks and Mental Health at Work in a Banking Institution

October 22, 2026

Digital Observatory of the Amazon: Data Science Applied to the Analysis of Social, Economic, Environmental, and Health Indicators

October 22, 2026

Continuous Learning as a Factor of Organizational Growth in the Perception of Collaborators

October 22, 2026

Statistical Regression in Microgrids for Operational Performance Estimation: Campusgrid Case

October 22, 2026

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

October 22, 2026

Stakeholder Engagement Factors in International Technology Transfer to a Public Hospital

October 22, 2026

Combating Commercial Electric Energy Losses Using a Time Series Model

The inclusion of children with Autism Spectrum Disorder (ASD) in Early Childhood Education presents significant challenges, given the difficulty of adapting to new environments and the intensity of stimuli. The objective was to analyze the teaching performance in Early Childhood Education in the initial schooling process of children with ASD. A case study was conducted, using narrative interview as a data production technique. The results revealed that the teaching performance was characterized by mediation and affection practices, with the flexibility of routine and the use of playful resources as essential strategies for the child’s development and sensory organization. The importance of the school support professional for the success of the pedagogical work was also highlighted. The child’s integral development was promoted through intentional teaching actions that prioritized environmental adaptation, strengthening of bonds, and attention to the specific needs of ASD. As a contribution, a guide of pedagogical strategies aimed at welcoming children with ASD in public daycare centers was developed.

Keywords: Early Childhood Education; School Inclusion; Teacher Narratives; Inclusive Pedagogical Practices; Autism Spectrum Disorder.

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

Psychosocial Risks and Mental Health at Work in a Banking Institution

Mental health in the workplace is a topic of growing relevance, impacting professional development and employee well-being. A study was conducted to identify aspects and situations that can influence absenteeism levels in a banking institution. The research involved 108 participants and used a structured questionnaire, based on the short version of COPSOQ II by Gonçalves (2021), which contained 45 closed Likert scale questions and two open-ended questions. Data were collected via an online platform and analyzed with a descriptive and quantitative approach. The results revealed a scenario that indicated the need for adjustments in the distribution of activities and in managers’ perception of behaviors and signs of disorders. Important evidence was identified in the participants’ open-ended responses. It was concluded that the study contributed to promoting the perception of a safe environment for mental health in the organization.

Keywords: Absences due to disorders; Professional development; Operational leadership; Medical leave; Mental health.

October 22, 2026

Digital Observatory of the Amazon: Data Science Applied to the Analysis of Social, Economic, Environmental, and Health Indicators

The state of Amazonas faced historical challenges in consolidating the Unified Health System (SUS), stemming from geographical barriers, socioeconomic inequalities, and structural limitations. This study described the development and implementation of a health information geoportal, designed to support monitoring, evaluation, and planning in the Amazonian context. A descriptive case study approach was adopted, based on documentary analysis and secondary data, covering the mapping of functionalities, technical infrastructure, and validation steps of the tool. The Portal was developed with open technologies and integrated multiple national databases, offering interactive dashboards, thematic maps, and a digital document repository. Among the results, highlighted were the georeferenced visualization of key indicators, the possibility of temporal comparative analyses, and the use of the platform in reviewing health plans and redirecting strategic actions. The portal can represent an advance in digital governance and evidence-based management, with potential for replication in other highly complex territories, provided it is accompanied by investments in technological infrastructure, professional training, and inter-institutional coordination.

Keywords: Amazon; Health Evaluation; Digital Health; Health Information Systems.

October 22, 2026

Continuous Learning as a Factor of Organizational Growth in the Perception of Collaborators

The impact of continuous learning and knowledge management on organizational growth was studied in a context of globalization and constant changes. The study’s objective was to analyze employees’ perception of learning culture and its importance for personal and professional development. Data were obtained through an anonymous survey, with a quantitative approach, using a form with “survey” type questions applied to 87 professionals from the technology, health, education, commerce, and services sectors. The results indicated that employees had a positive perception of the contribution of continuous learning to personal and organizational growth, recognizing its benefits for the development of new skills, innovation, and competitiveness. However, it was observed that the incentive for internal knowledge exchange and the offering of practical training still presented moderate levels of agreement. It was concluded that continuous learning significantly contributes to individual and organizational development, suggesting that companies should develop strategic policies for learning focused on new skills, aiming for greater competitive advantage and innovation.

Keywords: Continuous learning; Self-development; Organizational growth; Knowledge Management; Innovation.

October 22, 2026

Statistical Regression in Microgrids for Operational Performance Estimation: Campusgrid Case

A multiple statistical regression model was proposed to estimate the operational performance of UNICAMP’s CampusGrid microgrid, based on internal electrical quantities. The microgrid integrates photovoltaic generation, batteries, and a gas generator. Energy management system data were collected at five-minute intervals over one month. The Operational Reliability Index, defined as the ratio between supplied and demanded energy, was established as the dependent variable. The model was adjusted for the islanded operation mode, evaluating the impact of demand, state of charge, solar generation, and supplied energy. The results revealed high explanatory power, indicating that operational reliability depends on the interaction between supply and demand. It was observed that the nighttime period concentrated the highest rate of partial supply, attributed to the reduction in solar generation. It was concluded that multiple regression offers an interpretable and useful framework for microgrid monitoring and control strategy support.

Keywords: Battery storage; Photovoltaic generation; Reliability Index; Islanded operation; Energy Management System.

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.

October 22, 2026

Stakeholder Engagement Factors in International Technology Transfer to a Public Hospital

This study described the critical factors perceived for stakeholder engagement in international technology transfer in a public hospital, with a focus on planning. The objective was to describe these conditioning factors, according to the perception of professionals. A single case study was conducted, applying a questionnaire to 25 professionals and using content analysis, complemented by descriptive tabulations. The main obstacles identified were resistance to change (72%), funding (64%), lack of communication (60%), and bureaucracy (40%). Only 28% of respondents recognized the existence of adequate tools for stakeholder management, while 48% denied it and 24% did not know. Exploratory cross-tabulations indicated variations in the assessment of influence according to time of practice, but did not establish causal relationships. Lack of engagement was associated with delays, low adherence, waste of resources, communication failures, compromised knowledge absorption, and risks to patient safety. The conclusions were limited to the perceptions of the researched group and supported preliminary recommendations for intersectoral communication and coordination.

Keywords: Case study; Project Management; Health innovation; Stakeholders; Public sector.

October 22, 2026

Combating Commercial Electric Energy Losses Using a Time Series Model

Commercial losses of electric energy represented one of the main challenges for distributors, directly impacting economic sustainability and supply quality. The efficiency of time series models, focusing on exponential smoothing techniques, was evaluated in forecasting billed consumption of consumer units, to support the identification of deviations associated with non-technical losses. Historical data of monthly consumption from an electric energy distributor in Brazil were used, segmented by behavior profiles (stationarity, trend, and seasonality). Simple exponential smoothing models, Holt, and Holt-Winters (additive and multiplicative) were applied, compared to a traditional moving average. The Mean Absolute Percentage Error (MAPE) was the evaluation criterion. Additionally, the ETS approach was employed for automatic model selection and residual diagnostic tests, such as Ljung-Box and autocorrelation function analysis. The results demonstrated that more robust models showed a greater capacity for adaptation to the series’ characteristics and lower error, with a highlight on superior performance in scenarios with trend. For seasonal series, the ETS model showed a greater capacity for adaptation to transitions. It was concluded that the use of more structured time series models contributed significantly to the improvement of forecast accuracy and offered relevant analytical support for the identification of commercial losses and the optimization of operational and commercial processes in the electric sector.

Keywords: Energy distribution; MAPE; Optimization; Consumption forecasting; Exponential smoothing.

Economy

October 19, 2026

End of the 6×1 scale: what do the numbers allow us to conclude?

Following the promulgation of the end of the 6×1 shift system, the debate on the shorter workday moves to implementation and requires distinguishing social benefits from economic costs. The end of the 6×1 shift system transitioned from legislative discussion to a constitutional change in Brazil. On October 16, 2026, the National Congress promulgated Constitutional Amendment No. 141/2026, originating from Proposal […]

Artificial Intelligence

October 16, 2026

Why study if AI exists?

When answers become easy, learning comes to mean more than just arriving at them. Why do I need to learn this if I can ask an artificial intelligence? This type of question has accompanied education for decades. Why learn an operation if a calculator exists? Why memorize information if it can be found […]

Tax Management

October 15, 2026

Pink tax and the gender of price

How different marketing treatments for men and women are incorporated by consumption taxation Imagine a shelf on which two razors of the same brand and intended for the same purpose are displayed side by side: one has dark packaging and promises strength, precision, and efficiency; the other comes in shades of pink or […]

Health

October 13, 2026

The missing link in health transformation

Why is innovation not enough to drive changes in organizations and health systems Digital transformation has become a strategic priority for health systems worldwide. Electronic health records, artificial intelligence, telemedicine, remote monitoring, and data analysis are now part of the strategic agenda of governments and health organizations. Paradoxically, […]

Marketing

October 09, 2026

Bitcoin or pets: what Artificial Intelligence would not see

A real-life consumer intelligence case shows what gets left out of the brief A few years ago, an American insurance company hired a specialized consumer intelligence firm to answer three questions: The insurer was also considering launching paid insurance in bitcoin. At the time, the consultancy’s workflow was as follows: the analyst created a query […]

School Management

October 06, 2026

The school is not a casino: when trading cards become currency in the playground

Why, for certain students, does school manage to offer so few experiences of achievement? The World Cup is over. Brazil left the competition, the school holidays came, the final was played and the football calendar moved on. It would be reasonable to imagine that, with the end of the tournament and the return to classes, […] would also begin

Energy Transition

September 30, 2026

Renewable energies: the Brazilian advantage

Brazil needs to invest in the capacity to transform natural resources into innovation, productivity, and development. Talking about energy is talking about development. Behind industry, transportation, services, cities, and increasingly artificial intelligence, there is an energy infrastructure that sustains the economy. Understanding a country’s energy matrix is understanding […]

Data Analysis

September 30, 2026

When the data changes, has reality changed?

An analysis of almost 20 million teaching positions-year between 2020 and 2025 shows how changes in population composition and record production can alter the interpretation of historical series Between 2020 and 2025, the number of formal teaching employment positions identified in RAIS (Annual Relation of Social Information), from the Ministry of Labor, […]

Artificial Intelligence

September 28, 2026

Artificial intelligence and the trends

Why do so many people join in on the fun with ChatGPT? I was never the trend person. I still am not. Some pass through my timeline, I see them, I find them interesting but not to the point of trying them out. This was the case, inclusive, with some recent waves of images made by artificial intelligence, like the 80s trend, the one that […]

Tax Management

September 01, 2026

Tax reform and estate planning in the countryside

Efficiency in managing taxes facilitates governance and allows for the organization of family succession. Rural wealth organization has become a strategic measure in light of the tax reform in Brazil, which came into effect this year. The planning of activities and rural wealth management, through tools such as the transition from an Individual to […]

Renata de Gaspari Valdejão Almeida

Artificial Intelligence

August 05, 2026

Inside the company and off the radar: the risks of Shadow AI

According to Microsoft, 75% of professionals already use artificial intelligence at work without company approval. The use of generative artificial intelligence is already part of the corporate routine. Tools like ChatGPT, Copilot, and other platforms help professionals produce texts, analyze data, create presentations, and accelerate tasks in practically all sectors. But this advance […]

Renata de Gaspari Valdejão Almeida

Strategy

July 02, 2026

The future as a competence

Academic interest reinforces the projection of scenarios as an essential tool for decision-making. While some companies are still trying to get the next step right, others are already working with multiple possible futures — and preparing for all of them. But after all, what does it mean to “think about the future”? Is it a trend, a strategy, or a new competence that […]

Renata de Gaspari Valdejão Almeida

Innovation

Technology

May 21, 2026

Agro SP Corridor: innovation, institutional articulation and future

Pecege commands the executive operation of the 400 km ecosystem activities that became known as the Brazilian agro Silicon Valley In 2025, in addition to taking over the management of the Piracicaba Technology Park, the Pecege Institute was also designated to command the executive operation of the State Agribusiness Innovation Corridor activities, the so-called […]

Education

April 27, 2026

How to turn a TCC into a business

New management of the Piracicaba Technology Park offers consulting to MBA graduates The new project director of the Piracicaba Technology Park (PTP), Alexandre Barreto, often says that one of the greatest rewards he has ever had in life was seeing his MBA USP/Esalq students structure companies from their final projects […]

Technology

March 20, 2026

The human repertoire in the age of AI

Critical thinking and creativity are irreplaceable in the work of a marketing professional Artificial Intelligence (AI) is capable of incredible feats, but it does not yet possess the judgment, empathy, intuition, and strategic creativity necessary to do the job of a good marketing professional. In this area, it is important to know how to use the tool to automate […]

Renata de Gaspari Valdejão Almeida

Agribusiness

Innovation

February 23, 2026

ESG as a growth strategy in a cooperative in RS

Santa Clara balances social and environmental responsibility with innovation Founded in 1911 by Italian immigrants in Carlos Barbosa, in the Serra Gaúcha region, Cooperativa Santa Clara is an example that it is possible to balance economic growth with social and environmental responsibility. From a small cheese production company, the organization has evolved into a […]

Renata de Gaspari Valdejão Almeida

Agribusiness

Innovation

January 22, 2026

Brazil free of Foot-and-Mouth Disease: what changes for Brazilian beef?

With a herd of over 200 million head of cattle, the country is currently the leader in exports. Brazil recently received, for the first time, the certification of country free of foot -and-mouth disease without vaccination, conferred by the World Organisation for Animal Health (WOAH). The seal strengthens the country’s position as a reliable supplier of meat for the […]

Renata de Gaspari Valdejão Almeida

Innovation

December 09, 2025

Innovation: the new cycle of the Piracicaba Technology Park

Instituto Pecege assumes management, betting on the creation of new businesses Starting in 2026, Instituto Pecege will assume the management of the Piracicaba Technology Park (PTP). Among its responsibilities will be the administration, operation, maintenance, and expansion of the park, in addition to fostering activities in innovation, entrepreneurship, and science and technology. The choice was made […]

Renata de Gaspari Valdejão Almeida

July 06, 2026

Large-Scale Architecture: DSR-SCRUM Change Management

Mônica Alessandra Guerios; Maria do Carmo Assis Todorov Abstract generated by ResumeAI, an artificial intelligence solution developed by Instituto Pecege focused on synthesis and writing. Architecture and urbanism are configured as essential bases in an increasingly complex and challenging urban space, where the intrinsic connection between social, environmental, and technological issues […]