Improvement of the Goiano IPM through automatic classification of items in fiscal documents

doi:10.22167/2675-6528-202602655

Article

September 30, 2026

Improvement of the Goiano IPM through automatic classification of items in fiscal documents

Improvement of the Goiano IPM Through Automatic Classification of Items in Fiscal Documents

Allan da Costa Andrade; Abdoulaye Aboubacari Mohamed

DOI: 10.22167/2675-6528-202602655

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

The automation of fiscal data classification is crucial for improving tax management. The study developed, implemented, and evaluated machine learning models to automate the processing and classification of fiscal data used in the calculation of the Municipal Participation Index (IPM) in the State of Goiás, focusing on the identification of horticultural products traded at CEASA-Goiás. The research was based on the analysis of secondary data from electronic invoices from 2024, characterized by large volume and complexity. A quantitative, descriptive, and explanatory approach was adopted. The methodological process included data extraction, processing, standardization, and organization, as well as the construction of a supervised dataset for training, validation, and testing. Natural Language Processing techniques and supervised learning algorithms were used to classify fiscal item descriptions. Performance was evaluated by metrics such as accuracy, precision, recall, and consistency. The results achieved an accuracy of over 95% in identifying horticultural products. Compared to the manual process, a significant reduction in processing time, a decrease in inconsistencies, and an improvement in the integrity of the data used in the IPM calculation were observed. The automated solution contributed to greater transparency, reliability, and accuracy of fiscal information, optimizing the use of human resources. It was concluded that the application of data science and artificial intelligence techniques is an effective alternative for improving state tax management.

Keywords: Active Learning; Data Science; Tax Management; Municipal Participation Index; NF-e.

1. Introduction

The application of data science techniques has been widely expanded in the context of public management. The adoption of data science and machine learning methods is fundamental to extracting value and knowledge from large volumes of data, an imperative that extends to the optimization of public policies and fiscal processes (Fávero and Belfiore, 2021).

The Municipal Participation Index (IPM) is an instrument that proportionally distributes resources collected by the state among municipalities, considering economic and fiscal factors. In the State of Goiás, the methodology adopts total transparency, using granular data from all electronic fiscal documents. This approach generates a volume of approximately six billion invoice items, which, while ensuring transparency, imposes technical processing barriers.

The task of automatic classification of fiscal item descriptions can be understood as a classic text classification problem in Natural Language Processing. In these cases, unstructured data, often short and noisy, must be categorized automatically. This type of problem presents specific challenges related to high linguistic variability, semantic ambiguity, and low textual standardization (Manning et al., 2008).

Additionally, real fiscal bases, as those used in this study, tend to present class imbalance, in which certain categories have many more examples than others. This phenomenon is widely discussed in the machine learning literature, as it can lead models to present bias in favor of the majority classes, reducing generalization capacity (Fávero and Belfiore, 2021).

In fiscal contexts, the processing and correct categorization of electronic documents constitute relevant challenges, especially given textual variability and the complexity of tax rules. Laruccia (2022) demonstrated the feasibility of using Natural Language Processing models and machine learning for the automatic classification of electronic invoices. Interian et al. (2024), when analyzing Brazilian fiscal data for anomaly detection, highlight the importance of robust data mining techniques to ensure the integrity and compliance of information.

Despite the advances presented in the literature, a gap is observed in the integrated application of these approaches in real Brazilian fiscal contexts, especially in scenarios involving massive data, short and noisy descriptions, as well as significant class imbalance. There is a scarcity of studies that simultaneously explore these challenges in the context of fiscal item classification, also considering sectoral particularities, such as the fruit and vegetable segment and its influence on IPM calculation. Thus, the present work is inserted in this context, focusing on the classification of fruit and vegetable items from CEASA Goiás, aiming to avoid duplication in the IPM calculation base and contribute to greater accuracy and fairness in resource distribution. The objective of this work is to develop, implement, and evaluate machine learning models applied to the automation of the processing and classification of fiscal data used in the calculation of the Municipal Participation Index (IPM) in the State of Goiás, focusing on the identification of fruit and vegetable items traded at CEASA-Goiás.

2. Material and Methods

The methodological approach adopted in this study was based on consolidated data science and machine learning techniques. The research was characterized as descriptive and explanatory, seeking to determine the impact of automated classification on the accuracy of the Municipal Participation Index (IPM). The main design consisted of the implementation and evaluation of algorithms of

machine learning

, aligning with the research lines of automation and

strategic analytics

(Fávero and Belfiore, 2021; Manning et al., 2008).

The research used secondary data, originating from internal databases of the Goiás State Tax Administration. The information sources were the granular databases of electronic invoices (NF-e) from CEASA/CEARANA-Goiás. The temporal scope of the study focused on the year 2024, analyzing the massive volume of fiscal items for which the manual classification of fruits and vegetables demanded significant effort.

The initial methodological process included stages of data extraction, processing, standardization, and organization. Subsequently, a supervised base was built for training, validation, and testing of the classification models. The preliminary analysis involved a complete file with over 344,000 records, which would be classified binarily as produce or not produce.

The automatic classification of textual descriptions in fiscal documents falls within the context of classic short text classification problems. Such descriptions are characterized by high lexical variability, low semantic context, and the presence of noise, requiring specific preprocessing and modeling techniques (Manning et al., 2008; Salton and Buckley, 1988). Real fiscal databases often present class imbalance, which can compromise the predictive performance of models (Fávero and Belfiore, 2021).

The data preprocessing stage consisted of applying textual cleaning and normalization techniques (Manning et al., 2008). This included character standardization, accent removal, conversion of numbers to “NUM”, and elimination of duplicate spaces. Were used

stop words

such as “of”, “from”, “to”, “for”, “with”, “in”, “on”, “kg”, “un”, “und”, “cx”, “sc”, “gr”, “ml”, “gtin”, and “cm”, and a regular expression to remove isolated words.

For the representation of textual data, the choice was made for feature extraction based on n-grams, including unigrams, bigrams, and trigrams. This approach was chosen to capture semantic context in short descriptions, mitigating the ambiguity of isolated terms (Manning et al., 2008; Fávero and Belfiore, 2021). The TF-IDF technique was employed to transform textual data into numerical representations, reflecting the relative importance of terms in the corpus (Salton and Buckley, 1988).

The choice of classification algorithms considered their computational efficiency and suitability for textual classification problems in high-dimensional spaces. The Naive Bayes algorithm and the Passive-Aggressive Classifier, an online learning algorithm based on linear models, were used. Both are recognized in the literature for their good performance and generalization capability in scenarios with large data volumes and high textual variability (Manning et al., 2008; Ng and Jordan, 2002).

For the incremental and supervised construction of the training and validation bases, the technique of

engaged learning

(Settles, 2012; Marcacini and Rezende, 2012). This strategy aimed to prioritize the selection of more informative examples for the learning process, reducing supervision effort. Initially, a minimal supervised base of 700 records was built. The process followed an iterative flow of training, prediction, identification of the most uncertain cases, manual validation, and database update.

The dataset was divided into training (80%) and validation (20%) subsets, using stratified sampling to preserve the class proportion. This approach is relevant in scenarios with class imbalance, contributing to a robust evaluation of model performance (He and Garcia, 2009). Model evaluation was performed using quantitative classification metrics, including accuracy, precision, recall (

memory

), F1-score and confusion matrix analysis.

3. Results and Discussion

The research had as its main objective to develop, implement, and evaluate machine learning models to automate the classification of fiscal data, focusing on the identification of fruit and vegetable items traded at CEASA-Goiás, aiming to optimize the calculation of the Municipal Participation Index (IPM) in the State of Goiás. The results obtained demonstrate the viability and effectiveness of applying these techniques, culminating in an automated solution with high accuracy and significant improvements in tax management processes.

Initially, the information gathering involved the analysis of a complete file with over 344,000 electronic invoice records from 2024. The central task consisted of the binary classification of these items, determining whether or not they belonged to the fruit and vegetable category. This massive volume and the complexity of the data underscored the need for an automated approach to handle the technical processing and avoid barriers in the IPM calculation.

In the exploratory analysis of textual data, visualization tools such as word clouds were employed. The initial word cloud, based on 344,863 records, revealed the predominance of terms like “tomato” and “potato”, following Zipf’s Law. This frequency distribution, where a few terms concentrate most of the probability mass, indicated a bias challenge for machine learning, as the model might learn transaction frequency instead of discriminative semantic features.

The transition to a word cloud with 31,746 distinct records, obtained by removing duplicates, significantly altered the distribution of terms. This strategy reduced the influence of products with higher sales volume, highlighting a broader lexical diversity in the base and allowing less frequent items to become more visible. This approach was crucial for mitigating the bias caused by record repetition and identifying noise unrelated to the fruit and vegetable domain.

The identified scientific challenge was characterized as a problem of classifying short texts in noisy environments, where fiscal descriptions suffer from data scarcity and lack of syntactic context (Aggarwal & Zhai, 2012). The presence of non-standard prefixes and abbreviations required the vectorizer and the model to be robust to high lexical variance. The use of the TF-IDF technique was justified to penalize noisy terms with low discriminability and value specific technical terms, mitigating the impact of low semantic context (Salton & Buckley, 1988; Rossi, 2015).

The statistical analysis of the corpus revealed that the average number of words per record was 2.62, with 78% of the descriptions containing up to three terms. This behavior is characteristic of fiscal databases with short and unstructured descriptions, which hinders the extraction of meaning. To capture the semantic context in such concise descriptions, the choice was made for feature extraction based on n-grams (unigrams, bigrams, and trigrams), as recommended by Fávero and Belfiore (2021) and Manning et al. (2008).

The representation of textual data in numerical format, essential for machine learning algorithms, was performed using the TF-IDF technique. This configuration allowed capturing not only isolated words but also frequent composite patterns in fiscal descriptions, increasing the model’s discriminatory capacity. The choice of classification algorithms considered their computational efficiency and suitability for textual classification problems in high-dimensional spaces.

Dois algoritmos foram selecionados para o treinamento inicial: o Naive Bayes e o Passive-Aggressive Classifier. O Naive Bayes, baseado no Teorema de Bayes, é conhecido por sua simplicidade, baixo custo computacional e rápida convergência, sendo frequentemente utilizado como modelo de referência (Ng & Jordan, 2002). O Passive-Aggressive Classifier, por sua vez, é um algoritmo de aprendizado online baseado em modelos lineares, projetado para lidar eficientemente com grandes volumes de dados e descrições textuais de alta dimensionalidade (Manning et al., 2008).

For the training and validation of the models, the dataset was divided into training (80%) and validation (20%) subsets, using stratified sampling to preserve the proportion between classes. This approach is crucial in scenarios with class imbalance, contributing to a more robust and representative evaluation of model performance (He & Garcia, 2009). Accuracy, precision, recall, and F1-score metrics were used to measure performance.

In the first training, the Multinomial Naive Bayes model achieved an accuracy of 79.29%. Its classification report indicated a precision of 0.76 and recall of 0.95 for class 0, and a precision of 0.89 and recall of 0.57 for class 1. The confusion matrix revealed 78 correct predictions and 4 errors for class 0, and 25 errors and 33 correct predictions for class 1, showing greater difficulty in identifying the minority class.

In contrast, the Passive-Aggressive Classifier demonstrated superior performance in initial training, reaching an accuracy of 82.86%. For class 0, it achieved a precision of 0.80 and recall of 0.94, while for class 1, it reached a precision of 0.89 and recall of 0.67. The confusion matrix showed 77 correct predictions and 5 errors for class 0, and 19 errors and 39 correct predictions for class 1, indicating a greater capacity to correctly identify the minority class compared to Naive Bayes.

This superiority of the Passive-Aggressive Classifier can be attributed to its structural differences, especially its capacity to adapt to scenarios with high textual variability and dimensionality, as discussed by Manning, Raghavan, and Schütze (2008). However, it is important to note that these initial comparisons were based on point metrics from a single partitioning, without cross-validation or formal statistical tests, which requires caution in interpreting the differences.

Given the absence of a previously labeled and validated dataset, and the high volume of records, manual labeling of the entire dataset was unfeasible. Therefore, the “active learning” technique was adopted to prioritize the selection of the most informative examples for the learning process, reducing the human effort required in the supervision stage, as advocated by Settles (2012) and Marcacini and Rezende (2012).

The active learning strategy was based on the combination of two uncertainty criteria: the probability estimated by the Multinomial Naive Bayes model and the decision margin provided by the Passive-Aggressive model. A combined uncertainty score was calculated to prioritize samples with lower classification reliability. This process generated spreadsheets with product descriptions associated with the highest uncertainty values, indicating instances where the model had low decision confidence.

It was observed that descriptions related to mechanical components, for example, were correctly classified as non-horticultural products (Class 0), but with high uncertainty values. This suggested that the model made such classifications based on unrepresentative patterns, approaching the decision threshold. For Class 1 (horticultural products), products with composite or atypical descriptions, such as less common varieties, also showed lower prediction confidence.

The careful selection of these examples, located in the boundary region between classes, for manual review and subsequent incorporation into the training base, represented an efficient data enrichment strategy. By including instances from the uncertainty region, the classifier began to recognize previously ignored patterns, refining decision boundaries and reducing the error rate in subsequent iterations, according to Settles (2012) principles.

After adding 112 items to the training base through “active learning”, a new training was performed. The results indicated that the accuracy of Multinomial Naive Bayes was 78.53%, and that of Passive-Aggressive was 80.37%. This improvement was not significant, and in some cases, there was a slight decrease in accuracy, suggesting that the simple addition of data did not guarantee a linear improvement of the model.

In a subsequent step, 189 new items pointed out by “active learning” were included, using only the error probability of Multinomial Naive Bayes. With this new training, the accuracy of Multinomial Naive Bayes rose to 86.00%, and that of Passive-Aggressive to 87.00%. Although there was improvement, the performance evolution over the training cycles did not show to be linear, with more expressive initial gains and subsequent stabilization, indicating that the quality of the added data is more impactful than the quantity.

For the final evaluation of the models’ performance in a scenario close to the production environment, an independent validation base was built, composed of more than 30,000 records duly verified by the IPM management team. This base was used to ensure more representative metrics, excluding records selected for training to avoid overlap, as per the recommendations of Fávero and Belfiore (2021).

In the validation set, the Multinomial Naive Bayes model presented an accuracy of 88.10% for Class 1, while the Passive-Aggressive Classifier achieved 77.42% accuracy for the same class. The difference between training and validation performance was attributed to the greater diversity of descriptions in the validation set and the imbalance between classes, which reduced the model’s sensitivity to Class 1 in unseen data (Fávero & Belfiore, 2021).

The behavior of the Passive-Aggressive Classifier proved to be more stable between training and validation compared to Naive Bayes, which is expected for linear models with online learning on high-dimensional textual data (Manning, Raghavan & Schütze, 2008). The drop in Naive Bayes performance in validation reinforced the limitation of the conditional independence hypothesis between attributes, especially when the vocabulary of the validation set diverges from the training set.

The analysis of data preprocessing revealed that many values that did not distinguish the product were entering the classifier, generating confusion. To optimize the results, more rigorous preprocessing rules were implemented, including the removal of accents, the conversion of all numbers to the word “NUM”, the removal of duplicate spaces, and the inclusion of several keywords such as “kg”, “un”, “cx”, “sc”, “gr”, “ml”, “gtin”, “cm” in the stop words list, as well as a regex to remove standalone words.

Even with these treatments, the 95% classification barrier was not initially altered. A more in-depth analysis found that some items in the training set had only one example, which confused the classifier. To resolve this, the set was quadrupled, ensuring sufficient examples for the classifier in all training and testing divisions, which resulted in significant performance improvements.

After refining the preprocessing and expanding the training base, Multinomial Naive Bayes achieved an accuracy of 98.21% in training and 96.05% in validation, with 28,814 correct predictions and 1,186 errors in the validation base. This result demonstrated a substantial advance in the model’s ability to classify fiscal items for fruits and vegetables.

The Passive-Aggressive Classifier, with the same preprocessing and database expansion adjustments, achieved even higher accuracy, 98.81% in training and 96.54% in validation. In validation, 28,963 correct predictions and 1,037 errors were recorded. This superior performance of Passive-Aggressive reinforces its suitability for scenarios with high textual variability and large data volume, surpassing Naive Bayes in terms of final accuracy.

The final accuracy of 96.54% obtained by the Passive-Aggressive Classifier on the validation set is in line with the results reported in the literature on Brazilian fiscal document classification. Laruccia (2022), for example, achieved 96.7% accuracy with an ensemble classifier for binary classification of electronic invoices. This validates the effectiveness of the approach proposed and implemented in this study to improve state tax management.

In summary, the research demonstrated that the combination of Natural Language Processing techniques, supervised learning algorithms, and active learning strategies is an effective alternative for automating the classification of fiscal data. The accuracy exceeding 95% in identifying fruit and vegetable products, the reduction in processing time, and the improvement in data integrity confirm the contribution of the automated solution to greater transparency, reliability, and accuracy of fiscal information in IPM calculation, optimizing the use of human resources.

4. Conclusion

The present study sought to develop, implement, and evaluate machine learning models to automate the processing and classification of fiscal data, focusing on the identification of fruits and vegetables marketed at CEASA-Goiás, aiming to optimize the calculation of the Municipal Participation Index (IPM) in the State of Goiás. The feasibility and effectiveness of applying these techniques were verified, culminating in an automated solution that achieved over 95% accuracy in identifying fruits and vegetables. A significant reduction in processing time was observed compared to the manual method, along with a decrease in inconsistencies and an improvement in the integrity of the data used for IPM calculation. The combination of Natural Language Processing techniques, supervised learning algorithms, and active learning strategies proved to be an effective alternative for automating the classification of fiscal data. This automated solution contributed to greater transparency, reliability, and accuracy of fiscal information, optimizing the use of human resources and improving state tax management.

However, the study presented important limitations, such as the dependence on the quality of the original descriptions of fiscal documents and the restriction of the analysis to a single institutional context. Additionally, the comparisons between the models were based on punctual metrics from a single train and test partitioning, without the application of formal statistical significance tests, which requires caution in interpreting performance differences. For future studies, it is suggested to explore the application of cross-validation (k-fold) and formal statistical tests for a more robust comparison of classifiers. It is also recommended to use neural network-based models and class balancing techniques to further enhance generalization capability and sensitivity to minority classes in imbalanced datasets.

Bibliographic References

FÁVERO, L.P.; BELFIORE, P. 2021. Data Science para Negócios: Conceitos, técnicas e aplicações. 1ed. Elsevier, Rio de Janeiro, RJ, Brasil.

INTERIAN, R.; CARPANESE, I.; MELLO, B.; RIBEIRO, C. C. Red flag algorithms for Brazilian electronic invoices: outlier detection and price risk classification. International Transactions in Operational Research. Disponível em https://repositorio.usp.br/item/003154046 acesso em 12/10/2025: 1533-1553

LARUCCIA, J. B. Classificação automática de notas fiscais eletrônicas para utilização de créditos tributários de PIS/PASEP e COFINS. 2022. Trabalho de Conclusão de Curso (MBA) – Instituto de Ciências Matemáticas e de Computação, Universidade de São Paulo, São Carlos, 2022. Acessado em https://bdta.abcd.usp.br/item/003125927 dia 01/10/2025

MANNING, C. D.; RAGHAVAN, P.; SCHÜTZE, H. Introduction to Information Retrieval. Cambridge: Cambridge University Press, 2008.

SALTON, G.; BUCKLEY, C. 1988. Term-weighting approaches in automatic text retrieval. Information Processing

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

Most recent

Economy, Investments And Banking

October 23, 2026

Financial Education, Behaviors and Biases in Financial Decision Making

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

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

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

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.

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 […]