E&S Journal logo

Article

Technology

September 11, 2025

The covid-19 pandemic and the demand for air passenger transport on domestic flights

Authors: Laís Kimie Oshiro Caldeira and José Erasmo Silva

DOI: 10.22167/2675-6528-2023111
E&S 2025, 6: e2023111

The ability to predict the demand for a given service is a critical activity, yet it represents a challenge for managers in different industries. In the airline sector, demand forecasting impacts short-to-long-term planning, encompassing decisions about airport expansion or the construction of new ones, the planning of airlines, airport operators, and aircraft manufacturers, as well as the activities of other agents integrated into this complex supply chain[1].

The covid-19 pandemic, declared in 2020, unexpectedly affected the entire sector and frustrated any demand forecast projected for the subsequent months. According to the National Civil Aviation Agency (Anac)[2], in August 2021 – more than a year after the pandemic declaration – the number of passengers transported on domestic flights was still 30% lower than that recorded in August 2019.

Given this scenario, it becomes necessary to understand how demand reacted to the reduction of sanitary measures, the advancement of vaccination, and the recovery of other economic sectors. Thus, this study aims to identify a model capable of explaining the demand for air transport in the domestic market as a result of these factors, which provides a reference for future similar situations that impact the sector.

The first stage of this study consisted of data collection and processing. Public databases were used for the period from January 2020 to January 2022. Data from periods prior to 2020 were included solely for the purpose of discussing the results.

The dependent variable, which represents the phenomenon under study, is the demand for air passenger transport in the domestic market. The database used was extracted from the statistical data of air transport in Brazil, published by ANAC[3], which provides detailed information about the sector. To reflect the demand, the variable “paid passengers” was selected, filtering only information related to domestic flights, whether regular or non-regular.

Data of different natures were used as independent (or explanatory) variables. These variables are so named because they are used to explain the variations observed in the dependent variable. Information related to the pandemic, such as the number of daily new cases of covid-19, was extracted from the Ministry of Health’s coronavirus dashboard[4]. Records of vaccination against covid-19 in Brazil were obtained from the Coronavirus Pandemic[5] database with information regarding the percentage of vaccinated people, fully vaccinated people, and those who received the booster dose.

The airfare was also considered, extracted from the microdata of commercialized airfares, published by ANAC[6]. The monthly average fare was used, calculated from the weighted average between the prices charged and the number of tickets sold. Furthermore, data on the price of aviation fuel were incorporated, used as an instrumental variable for the value of tickets, extracted from the aviation fuel price table provided by Petrobras[7], from which the national average was obtained.

Finally, data regarding employment level and Gross Domestic Product (GDP) were extracted from the Ipeadata portal, including the “Labor force participation rate”[8] – which corresponds to the percentage of people in the labor force in relation to the working-age population – and the monthly GDP records[9]. Table 1 presents a summary of the final database used. All records were organized with monthly periodicity.

Table 1. Database summary

VariableAverageMaximumMinimumStandard deviation
domestic_passengers4.612.9439.304.796399.5572.401.210
vaccinated_people23,03%79,59%0,0%31,62
fully_vaccinated*15,15%70,06%0,0%24,07
booster_dose*1,87%22,09%0,0%5,13
new_covid_cases1.017.0703.139.2230,0%801.052,8
average_rate*402,70561,20263,1086,22
qav_price2.3433.6441.209666,55
workforce_percentage60,38%63,40%56,70%1,98
gdp_million_reais674.940759.981555.38762.786,79
Source: Original research results.
Note. *Variables not used in the regression models that will be presented; as the data were organized on a monthly basis, for each variable there are 25 records (from Jan. 2020 to Jan. 2022).

For the simulation and choice of the most suitable model for explaining demand, multiple linear regression technique was applied, based on the ordinary least squares (OLS) method. The estimated model assumes the form presented in Equation 1:

where:
Y: dependent variable;
α: intercept;
βj (j = 1, 2, …, k): coefficient of each independent or explanatory variable;
Xj (j = 1, 2, …, k): explanatory variable.

After evaluating the significance of the model through the F statistic, the stepwise procedure was applied, an automated method that allows the selection of statistically significant variables in linear regression[10]. Subsequently, the Shapiro-Wilk test was performed to verify the normality of the error terms, indicated for samples with fewer than 30 observations. The process was repeated for different models, with inclusions and alterations of variables to find the best-fitting model, using R² as the main reference. This measure, known as the coefficient of determination, indicates how much of the dependent variable can be explained by the independent variables, ranging from zero to one (the closer to one, the greater the explanatory power of the model).

After testing initial models and verifying the adequacy of the database, it was decided to use the variable “people_vaccinated” to represent vaccination-related information and “preco_qav” to reflect the impact of the “average_tariff” on demand.

The first model was simulated with all selected variables. By the OLS method, the model presented a p-value of the F statistic of 0.004, which indicates that at least one of the explanatory variables has a coefficient (β) statistically different from zero. Initially, only the employment level variable proved to be statistically significant at a 1% significance level. After the stepwise procedure, GDP was included with 10% significance.

The Shapiro-Wilk test confirmed the adherence of the model’s residuals to the normal distribution, with a p-value of 0.9972 (the p-value should be greater than 0.05, with 5% significance). For the purpose of comparison between models, this first one will be called “absolute without dummies”, as the data were used according to their original values (absolute values), without “dummy” variables for seasonality (also called binary, these variables are created to represent non-numeric, or categorical, variables, assuming the value of 1 to indicate the presence of a certain characteristic and 0 to indicate its absence). Equation 2 describes the first model and allows visualizing the relationship between the variables:

where:
pass: number of domestic passengers;
empr: employment level;
gdp: Brazil’s Gross Domestic Product in millions of reais.

A brief analysis indicates that the correlation between the employment level and GDP is positive in relation to the demand for domestic flights, that is, when GDP or the employment level increase, a greater number of passengers is expected. However, no variable related to the pandemic showed statistical significance.

In the second model, the difference between consecutive periods was applied to the variables instead of the absolute values. For example, for the variable “number of passengers”, the difference between consecutive months was used, in mathematical terms:

where:
∆passengers_t: variation of passengers in month t;
passengers_t: quantity of domestic passengers in month t;
passengers_t-1: quantity of domestic passengers in month t-1.

This approach corresponds to the first-differences method or first-differences, suitable for time series to eliminate the bias caused by possible omitted variables in the model. However, the model did not prove to be statistically significant.

In the third model, only percentage data was used. Thus, all variables were transformed into percentage variations relative to the previous period:

where:
passengerst: percentage variation of passengers in month t;
domestic passengerst: quantity of domestic passengers in month t;
domestic passengerst-1: quantity of domestic passengers in month t-1.

By the OLS method, the “percentage without dummies” model presented an F-statistic p-value of 0.003. Therefore, at a 5% significance level, it is concluded that at least one of the explanatory variables has a coefficient (β) statistically different from zero. The variables “vaccinated people”, “employment level”, and “GDP” were statistically significant before and after the application of the stepwise procedure. In the Shapiro-Wilk test, the residuals showed adherence to normality.

This model presented an R² slightly higher than the “absolute without dummies” model (0.67 versus 0.65 of the first model). However, the interpretation of the “percentage without dummies” model is more complex and presents some correlations contrary to expectations. Equation 5 illustrates this model:

where:
∆pass: percentage variation in the number of passengers transported in relation to the previous period;
empr: employment level;
vac: percentage of vaccinated people;
∆pib: percentage variation of GDP in relation to the previous period.

The interpretation of this model can be carried out as follows: with the other variables constant, a one percentage point (p.p.) increase in the employment level would imply a 19.17% reduction in the number of passengers transported in relation to the previous period; a one p.p. increase in the proportion of vaccinated people would represent a 0.78% increase in the number of passengers transported; finally, a 1% GDP growth would correspond to a 2.92% increase in the number of passengers transported. Among the estimated coefficients, the negative correlation between employment and the number of passengers stands out, contrary to what would be intuitively expected.

Although both models present a relatively adequate fit to explain demand behavior, it is known that the air transport market presents seasonality, with peaks in the school holiday months, which was not incorporated into these initial models. Figure 1 presents the evolution of domestic air transport demand over the last five years and shows that the months of December, January, and July have a peak compared to others, even during the pandemic, except for July 2020.

Figure 1. Seasonality of domestic flight demand
Source: ANAC (2022a).

To obtain more adjusted models that considered seasonality, new models were tested with the insertion of binary variables (or “dummies”) for each month and year in the database. This means that for each month and year, an indicator variable was created that assumes a value of 1 when the observation belongs to that period and 0 otherwise. All models proved to be significant by the F statistic and with residuals adhering to normality, according to the Shapiro-Wilk test. However, the models with all “dummies” for years and months or only for months are difficult to interpret due to the excess of variables. These models were inadequate for a broader understanding of the pandemic’s impact on demand for domestic flights, due to overfitting, that is, the estimated data adjusted excessively to the base, making the model not very robust for estimating any distinct future values.

The model with “dummies” only for the years presented more interesting coefficients, with employment level and GDP variables behaving similarly to the “absolute model without dummies” and an R² of 0.71. However, the use of a specific “dummy” for the year 2021, for example, harms the model’s generalization. After tests with variables in absolute and percentage values, the inclusion of “dummies” for months and/or years did not result in models capable of satisfactorily capturing the demand variation caused by the pandemic for future analyses.

In another effort to capture seasonal variation in demand, two other models (with absolute and percentage values) were tested with a dummy variable indicating high season in the months of December, January, and July.

Both models proved significant by the F statistic and with residuals adhering to normality after applying the Shapiro-Wilk test, in addition to solving the overfitting problem. Furthermore, all correlations were as expected: the increase in GDP or employment level resulted in an increase in demand. The model with absolute values, referred to as “absolute high season”, did not incorporate variables related to the pandemic. The model with percentage variations showed the same results and coefficients as the “percentage without dummies” model, and the variable referring to high season was not statistically significant. After analyzing the discussed models, Table 2 compares the models that best represent demand behavior based on R2.

Table 2. Comparison of candidate models

Source: Original research results.
Note. ***p < 0.001; **p < 0.01; *p < 0.05; the number format is as per the system output, therefore, decimal places are separated by a point instead of a comma.

The “absolute high season” model was chosen for presenting the highest R² (0.75), which demonstrates a better capacity to explain the behavior of demand for domestic air transport. Furthermore, the model does not include pandemic-specific variables, which increases its generalization and allows for future application. Equation 6 represents the selected model:

Where:

pass: number of domestic passengers;

employment level;

GDP: Brazil’s GDP in millions of reais;

high: binary variable indicating high season.

The interpretation of this model can be carried out as follows: with the other variables constant, a one percentage point (p.p.) increase in employment level implies an increase of 784,442 passengers transported; for each million reais more in GDP, an increase of nine passengers transported is expected; during the high season period (January, July, and December), an increase of 1,678,927 passengers transported is observed.

Although the variables related to the pandemic are not contemplated by the model, they show a correlation with demand (Figure 2). When there is a reduction in covid-19 cases, an increase in demand is observed. Similarly, as vaccination in the country advances, an increase in demand is verified.

Figure 2. Evolution of demand for domestic air passenger transport, the quantity of new covid cases, and the percentage of vaccinated people
Sources: ANAC (2022a), Ministry of Health (2022), and Our World in Data (2022).

Figure 3 shows that the evolution of vaccination is highly correlated with GDP and employment levels. Furthermore, the number of new covid-19 cases is also significantly related to GDP. These links help explain the absence of specific pandemic variables in the model, as their impact is indirectly reflected by the two macroeconomic variables. In fact, this result favors the generalization of the model and its application in possible future events that similarly impact the dynamics of society and the economy.

Figure 3. Correlation between variables related to the covid-19 pandemic, GDP and the employment level
Source: Original research results.

Gudmundsson et al.[11] highlight the historical relationship between GDP and demand for air transport. The model developed in this work confirms this relationship even during the pandemic period.

Figure 4 presents a comparison between the actual values of the quantity of domestic passengers and the values predicted by the extrapolated model for the period of the last five years. The estimated values reflected the seasonality of demand, even for data prior to the pandemic. However, the difference between the actual values and the estimated values was greater in the previous period.

Figure 4. Comparison between actual and estimated domestic passenger volume
Source: ANAC (2022a) and original research results.

Next, a new regression was performed with data from the last five years (since January 2018), in which the variable “passengers” was defined as dependent and “GDP”, “employment level”, and “high season” as explanatory. This new model, named “test i”, showed only employment level and high season as statistically significant variables. Furthermore, its residuals did not adhere to normality. However, the results allowed for some relevant observations. Figure 5 presents a comparison between the actual number of passengers and the estimated demands.

Figure 5. Comparison between the actual and estimated number of domestic passengers (model and test i)
Source: ANAC (2022a) and original research results.

The predicted demand for the pre-pandemic period by the “test i” model is closer to the actual demand compared to the original model’s estimate, and for the post-pandemic period, the difference was also not significant.

When simulating another model called “pre-covid test”, with the same variables (passengers, GDP, employment level, and high season) for the period between 2018 and 2019, the only statistically significant variables were “GDP” and “high season”. Figure 6 presents the real demand compared to the estimated demands.

Figure 6. Comparison between actual domestic passenger volume, estimated (model, test i and pre-covid test)
Sources: ANAC (2022a) and original survey results.

Without the inclusion of the employment level, the “pre-covid test” model does not capture the significant drop in demand after the pandemic. Figure 7 shows why the employment level is relevant when considering data after March 2020. The employment level shows a sharper drop and a more gradual recovery, a pattern similar to that observed in the demand for domestic air transport. GDP, on the other hand, shows signs of recovery two months after the declaration of the pandemic, and its drop is not as sharp. Therefore, the estimated model considers GDP as a significant variable for demand forecasting, but highlights the importance of the “employment level” in capturing the effect of crises, such as the covid-19 pandemic.

Figure 7. Evolution of employment level and GDP
Source: Ipeadata (2022a; 2022b).

It is important to highlight some limitations of the results. In the domestic market, the absence of flight restrictions between cities allowed for a simpler demand analysis. In international contexts, regulatory factors, such as vaccine or quarantine requirements, would make the analysis more complex. Therefore, when extrapolating the results, the specific context in which the model was developed should be considered. It is also necessary to monitor possible structural changes in the labor market, such as the advancement of remote work, which may affect the model’s premises. Furthermore, the model only covers the post-pandemic recovery period and is limited to linear relationships between variables — nonlinear approaches could be explored in future studies.

In conclusion, the model offers value to airlines, airport operators, and public policymakers by guiding strategic decisions related to capacity, routes, fleet, pricing, and infrastructure investments. In addition to its utility in regular operational scenarios, it also stands out as an effective tool for dealing with disruptive events, such as pandemics or economic crises. When integrated with periodically updated economic projections or applied in simulations and stress tests, the model allows for rapid estimation of demand drops, projection of network readjustment, sizing of teams, renegotiation of contracts, and calibration of subsidy policies, which contributes to reducing the negative impacts on the sector.

The results of this study were successful in estimating demand in a way that is compatible with the effects observed during the pandemic, and the tool demonstrates potential to support continuous market monitoring and projections in similar future scenarios.

REFERENCES

[1] International Civil Aviation Organization (ICAO). 2006. Manual on air traffic forecasting. 3ed. International Civil Aviation Organization.

[2] Agência Nacional de Aviação Civil (ANAC). 2021. Em agosto, indicadores do transporte aéreo permanecem abaixo dos níveis de 2019. Disponível em: <https://www.gov.br/anac/pt-br/noticias/2021/em-agosto-indicadores-do-transporte-aereo-permanecem-abaixo-dos-niveis-de-2019>. Acesso em: 31 out. 2021.

[3] Agência Nacional de Aviação Civil (ANAC). 2022a. Dados Estatísticos do Transporte Aéreo do Brasil. Disponível em: <https://www.gov.br/anac/pt-br/assuntos/dados-e-estatisticas/dados-estatisticos/dados-estatisticos>. Acesso em: 07 abr. 2022.

[4] Ministério da Saúde. 2022. Painel Coronavírus. Disponível em: https://covid.saude.gov.br/. Acesso em: 07 abr. 2022.

[5] Our World in Data. 2022. Coronavirus Pandemic (covid-19) Vaccinations. Disponível em: https://ourworldindata.org/covid-vaccinations. Acesso em 07 abr. 2022.

[6] Agência Nacional de Aviação Civil (ANAC). 2022b. Tarifas Transporte Aéreo Passageiros Domésticos. Disponível em: https://www.gov.br/anac/pt-br/assuntos/dados-e-estatisticas/microdados-de-tarifas-aereas-comercializadas. Acesso em: 07 abr. 2022.

[7] Petrobras. 2022. Preços de Vendas de Combustíveis. Disponível em: https://petrobras.com.br/pt/nossas-atividades/precos-de-venda-de-combustiveis/. Acesso em: 17 abr. 2022.

[8] Instituto de Pesquisa Econômica Aplicada (IPEA). 2022a. Ipeadata – Taxa de participação na força de trabalho das pessoas de 14 anos ou mais de idade, na semana de referência. Disponível em: http://www.ipeadata.gov.br/Default.aspx. Acesso em: 07 abr. 2022.

[9] Instituto de Pesquisa Econômica Aplicada (IPEA). 2022b. Ipeadata – Produto Interno Bruto PIB. Disponível em: http://www.ipeadata.gov.br/Default.aspx. Acesso em: 07 abr. 2022.

[10] Oxford University Press. 2008. A Dictionary of Statistics (2 ed.). Oxford: Oxford University Press. ISBN 9780199541454. Disponível em: https://www.oxfordreference.com/display/10.1093/acref/9780199541454.001.0001. Acesso em: 04 set. 2025.

[11] Gudmundsson, S.V.; Cattaneo, M.; Redondi, R. 2020. Forecasting temporal world recovery in air transport markets in the presence of large economic shocks: The case of COVID-19. Journal of Air Transport Management 91. Disponível em: https://doi.org/10.1016/j.jairtraman.2020.102007. Acesso em: 07 abr. 2022.

COMO CITAR

Caldeira, L.K.O.; Silva, J.E. 2025. A pandemia de covid-19 e a demanda pelo transporte aéreo de passageiros em voos domésticos. Revista E&S. 6: e2023111.

ABOUT THE AUTHORS

Laís Kimie Oshiro Caldeira – Master in Transport and Public Policy and Specialist in Data Science and Analytics. Chicago, Illinois, USA.

José Erasmo Silva – Advisor professor. Federal University of Bahia. Postgraduate Program in Accounting (PPGCONT), Avenida Reitor Miguel Calmon, s/n Canela,40231-300, Salvador, Bahia, Brazil.

Download this article in PDF

Most recent

October 02, 2026

Determinants of supermarket location in São Paulo

Neuroscience And Learning In Education

October 02, 2026

Anti-Racist Education: Inclusive Educational Practices and Social Development

Neuroscience And Learning In Education

October 02, 2026

Paths of Inclusion: Perceptions of Parents and Teachers on the Schooling of Students with Dual Exceptionality in the Brazilian Context

October 02, 2026

Predictive modeling for inventory management: increased productivity and efficiency in a food distribution center

October 02, 2026

Data Transformation into Strategy: Applied Research for Ecotourism Operation Optimization

October 02, 2026

Classification of defaulting customers using supervised machine learning techniques

October 02, 2026

Sentiment Analysis on Brazilian Banks on Twitter/X: Comparison between Traditional and Digital Institutions

October 02, 2026

Optimization of annual budget planning through project management methodologies

October 02, 2026

Innovation in traditional business models and its impact on the workplace

You may also like

Technology

December 08, 2025

Innovation and profitability in technology companies: a case study

Authors: Ryller Sousa de Moura and Marco Antonio Alves de Souza Junior DOI: 10.22167/2675-6528-2025038E&S 2025, 6: e2025038 Every business leader faces a constant dilemma: the pressure for short-term results, expressed in healthy profit margins, versus the need to invest in innovation to ensure the company’s future relevance and growth. This […]

Technology

October 23, 2025

Optimization of tax audit actions through company ranking using machine learning

Authors: Giovana Amorim Zanato and Cláudio Tucci Junior DOI: 10.22167/2675-6528-2024082E&S 2025, 6: e2024082 Fiscal audit is a central element of tax collection and compliance in the public sector, it ensures the correct application of norms and plays a strategic role by enabling public policies through collected revenue[1]. With the transition of the Tax on Circulation of Goods […]

Technology

September 04, 2025

Financial inclusion of countries developing Central Bank Digital Currency through the clustering technique

Authors: Magali Susana Chalela and Anna Carolina Martins DOI: 10.22167/2675-6528-2024051E&S 2025, 6: e2024051 The Bank for International Settlements (BIS)[1] issued a report in 2022, in which it highlighted that more than 90% of central banks, representing 82% of the world population and 94% of all global economic capacity, are developing or studying Central Bank Digital Currency […]

Digital Consumer

Strategy

Innovation

Marketing

Technology

July 29, 2025

Humanization resources in the development of creatives for paid traffic

DOI: 10.22167/2675-6528-2025005E&S 2025, 6: e2025005 Natália Kurebayashi Velloso and Nicole Verci Mostagi Segundo Camargo[1] and Lindstrom[2], neuromarketing explores consumer behavior and reveals the essential role of emotions in purchasing decisions. Faced with a dynamic market, companies need to innovate to remain competitive[3]. Neuromarketing is a tool to understand and […]

Technology

May 14, 2025

Influence of agile work on the motivation of technology professionals

DOI: 10.22167/2675-6528-2025006E&S 2025, 6: e2025006 Vlademir Lenin Donato Batista and Paulo Roberto Palauro One of the central challenges in people management, especially in the dynamic information technology (IT) sector, is to cultivate and sustain team motivation. Ensuring that professionals remain productive, engaged, and satisfied with their work is fundamental to ensuring […]

Technology

March 25, 2025

Data management in scientific research: ethical approaches and integrity practices

DOI: 10.22167/2675-6528-20240052E&S 2025, 6: e202400052 Ana Paula Lopes Marinho and Alex Nunes de Almeida With the growing availability of digital data and the use of Artificial Intelligence (AI) and Machine Learning (ML) methods in data science, a new paradigm emerges for information management and security. Scientific production, based on […]

Strategy

Industries

Innovation

Technology

September 20, 2024

New Industry 4.0 technologies in the corporate environment

DOI: 10.22167/2675-6528-20240024E&S 2024, 5: e202400024 Rodrigo Augusto da Silva; Dayane Freire Romagnolo The Fourth Industrial Revolution, known as Industry 4.0 or I 4.0, is a movement initiated in Germany around 2012 that continues to advance to the present day. The initial idea was to unite companies, universities, and government to promote technological advancement and […]

Technology

July 31, 2026

The world through a systemic lens

From software to social relations, how analyzing systems helps understand complex problems The word “system” is part of our vocabulary and appears frequently in services and activities related to technology. The association is understandable: digital systems are present at work, in studies, in shopping, in communication, in transportation, and in entertainment. Often, we only […]

Technology

July 10, 2026

AI in education: the challenge of responsibility

Smart technologies require governance, teacher training, and critical thinking to avoid deepening inequalities Artificial intelligence is consolidating itself as one of the most relevant forces of contemporary digital transformation, and education has come to occupy a central place in this movement. If before the discussion revolved around the digitalization of content and the expansion of teaching […]

Technology

July 01, 2026

From Papa Pop to Papa Tec

Technology, human dignity, and the unlikely consensus on artificial intelligence When Humberto Gessinger composed O Papa é Pop, in 1990, he observed a curious phenomenon of modernity: even one of the most traditional figures in the world had been absorbed by media logic. The Pope no longer resided only in temples. He was on magazine covers, in […]

Technology

December 03, 2025

Fraud detection: how AI redefined financial security

Fraudsters adapt quickly, which demands continuous evolution in protection systems. Financial fraud continues to be one of the biggest challenges of the digital economy. In 2022 alone, losses exceeded 1.2 billion euros in the United Kingdom and 8.8 billion dollars in the United States (Khalid et al., 2024). This highly dynamic environment […]

Data Science Analytics

Technology

September 26, 2025

The churn and data science: new frontiers in customer retention

Predictive approaches capture subtle behavioral patterns and allow for the anticipation of dissatisfaction signals. Customer retention has become one of the pillars for the sustainability and growth of companies in the face of contemporary competitiveness. Customer loss, or churn, represents not only the interruption of a revenue stream but also additional costs associated with […]

Innovation

Startups

Technology

September 01, 2025

The curse of the free PoC

In the best practice of open innovation, the ideal is for startups and corporations to maintain a fair relationship. Building partnerships is fundamental in the innovation ecosystem for value generation among its agents. In this context, investors and early adopters are important parties for the startup gears to start […]

Ai

Marketing

Technology

August 21, 2025

Marisa Maiô’s artificial intelligence

When creativity meets memory and activates a generation’s repertoire I was scrolling through the reels feed on Instagram when I was surprised by a talk show worthy of Silvio Santos and Casos de Família — all at the same time. The saturated colors, the sharp cuts, the witty jokes, and a certain nostalgia […]

Data Science Analytics

Financial Institutions

Technology

August 05, 2025

AI and default in Brazil: new tools

The use of predictive models is already revealing hidden layers in the data, allowing for the identification of patterns and the anticipation of behaviors. The Brazilian economic scenario in the first half of 2025 presented an increase in default rates, a trend that has been observed since 2022 and has been a recurring concern for governments and financial institutions […]

Education

Writing

Technology

June 26, 2025

Challenges of humorous reproduction in subtitling translation

The translator’s work demands a high degree of cultural sensitivity and creativity, in addition to linguistic competence. The role of the subtitling translator is not — and should not be — merely to translate its content literally. It is necessary for them to consider the cultural aspect, along with the main objective of the work, that is, its essence […]

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 […]

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

Digital

Education

Technology

August 25, 2025

Artificial intelligence cuts costs and redefines productivity

Implementing AI in business can be easier than you imagine, but it requires preparation. You get into a brand new modern car, but you don’t adjust the seat, you don’t learn to turn on the air conditioning or control the sunroof, in short, you don’t bother to know how to use the available accessories and tools. You will be able to […]

Renata de Gaspari Valdejão Almeida

Education

Innovation

Technology

June 16, 2025

Digital Gap: Is Brazil prepared for the technological revolution?

From 2019 to 2024, the market opened 665,000 vacancies, but only 464,000 professionals graduated, a deficit of 30.2%. A report released by Brasscom (an entity representing technology companies in Brazil) projects that the sector should generate between 30,000 and 147,000 formal jobs in the country by the end of […]

Renata de Gaspari Valdejão Almeida

Innovation

Technology Parks

Technology

May 21, 2025

Brazilian technology parks: next steps

The country already has more than 100 hubs and needs to modernize governance to foster competitiveness and development Innovation is one of the most important words today. It is through it that companies can improve their competitive positioning, generate new jobs and, with that, contribute to the generation of business value and to […]

Renata de Gaspari Valdejão Almeida

Agribusiness

Innovation

Technology

April 14, 2025

Tools monitor risks and help expand rural credit

Disbursement of the 2023/24 Safra Plan was 13% higher than the previous one Brazil has experienced an expansion in rural credit lines, stimulated by both public policies and private banks. The disbursement of the 2023/24 Safra Plan, for example, reached R$ 373.4 billion in the period from July/2023 to May/2024. A 13% increase in […]

Renata de Gaspari Valdejão Almeida

Digital

Education

Technology

January 17, 2025

The new profile of the professional of the future

“Technology doesn’t work alone; it’s people and technology that will do increasingly productive and differentiated work.” The job market is undergoing an accelerated process of specialization. New fields of activity emerge all the time, driven by technological evolution. The news is good, because it heralds the emergence of more opportunities for […]

Renata de Gaspari Valdejão Almeida

Technology

December 10, 2025

Performance comparison between Machine Learning and Generative AI in emotion detection

Author: Carlos Eduardo Frantz Manchini — Advisor: Thiago Gentil Ramires Abstract generated by the ResumeAI tool, an artificial intelligence solution developed by Instituto Pecege focused on synthesis and writing. This work compared traditional machine learning models with the Hume AI Generative Artificial Intelligence solution in the task of inferring emotions from the RAVDESS audio database. […]

Technology

December 10, 2025

Critical factors in the implementation of Design Systems and their competitive impact

Author: Lucas Yuji Botelho Ozaki — Advisor: Natan De Souza Marques Abstract generated by the ResumeAI tool, an artificial intelligence solution developed by Instituto Pecege focused on synthesis and writing. This study investigated the determining factors for success or failure in the implementation of a Design System and evaluated whether companies that adopted the methodology of […]

Technology

December 10, 2025

Development and evaluation of predictive models for heart disease

Author: Luis Enrique Icart Maciel — Advisor: Fábio Lima Abstract generated by the ResumeAI tool, an artificial intelligence solution developed by Instituto Pecege focused on synthesis and writing. This study sought to develop and evaluate predictive models for heart disease using open data, focusing on identifying the most influential variables. Building machine learning algorithms […]

Technology

December 10, 2025

Analysis of parliamentary spending patterns through clustering

Author: Dalciana Bressan Waller — Advisor: Eder Costa Cassettari Abstract generated by the ResumeAI tool, an artificial intelligence solution developed by Instituto Pecege focused on synthesis and writing. The objective of this research was to investigate the spending patterns of Brazilian federal deputies with the Quota for the Exercise of Parliamentary Activity (CEAP), using clustering techniques […]

Technology

December 10, 2025

Global control of positions and people for efficient decisions in multinational corporations

Author: Bianca Cuba Bersan — Advisor: Fernando Celso De Campos Abstract generated by the ResumeAI tool, an artificial intelligence solution developed by Instituto Pecege focused on synthesis and writing. This work develops a management panel (dashboard) to integrate and visualize data from dispersed teams, allowing efficient control, information analysis, and strategic calculations such as budget planning […]

Technology

December 10, 2025

Predictive models for inventory management with time series in the implement industry

Author: Mariana Prignacca — Advisor: Vanessa Mesquita Blas Garcia Abstract generated by ResumeAI, an artificial intelligence solution developed by Instituto Pecege focused on synthesis and writing. This work explores Box-Jenkins family time series models and exponential smoothing to forecast the demand for agricultural implement spare parts, using a series […]