Fraud detection: how AI redefined financial security

Column

Technology

December 03, 2025

Fraud detection: how AI redefined financial security

Fraudsters adapt quickly, which requires continuous evolution in protection systems

Financial fraud continues to be one of the biggest challenges in 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 requires financial institutions to move away from reactive actions and adopt increasingly sophisticated predictive approaches.

The digitalization brought efficiency, but also expanded the opportunities for fraud. Technologies like Chip & PIN reduced in-person fraud, but stimulated the migration of attempts to the online environment, especially in Card Not Present (CNP) transactions (Edge & Sampaio, 2009). In this scenario, fraudsters adapt quickly, which requires continuous evolution in detection systems.

Historically, fraud detection relied on fixed rules, like “if X happens, block”. These were simple and predictable systems, easily bypassed. The first major shift occurred with machine learning, which began to learn patterns directly from data, allowing the identification of behaviors outside the norm (Carcillo et al., 2021).

At this stage, two groups of techniques emerged: (1) supervised models, trained with transactions labeled as legitimate or fraudulent, and (2) unsupervised models, capable of detecting anomalies without relying on labels, especially useful for novel frauds.

This stage also consolidated the importance of feature engineering. Behavioral variables such as sum of expenses, transaction frequency, temporal variations, and patterns by locality significantly expanded the capacity of models to capture subtle deviations (Seera et al., 2024).

Deep learning in action

With the popularization of neural networks, a new technological leap emerged. While the first architectures analyzed isolated transactions, models like LSTMs began to capture the sequential behavior of the user, identifying patterns over time (Roseline et al., 2022; Jurgovsky et al., 2018).

This type of analysis contextualizes the transaction. A purchase may seem legitimate in isolation, but deviate from the client’s recent pattern, and LSTMs capture exactly that.

Beyond the transactional level, neural networks have also been applied to identify fraud risk at the organizational level, with models capable of analyzing internal and external factors and achieving accuracy greater than 90% (Krambia-Kapardis et al., 2010).

Graphs and advanced detection

The current frontier of fraud detection is dominated by Graph Neural Networks (GNNs). Unlike models that analyze individual users only, GNNs consider the entire ecosystem as a connected network. Customers, devices, IP addresses, merchants, and transactions form a dynamic graph.

This approach allows for the identification of fraud rings, suspicious connections between accounts, coordinated patterns among multiple users, and recurrent use of fraudulent devices. Graph-based models have been delivering superior results in detecting organized and sophisticated fraud (Chen et al., 2024; Zhu et al., 2021).

Challenges

Despite the advances, implementing AI in production brings concrete challenges. The first is the strong data imbalance. Fraud represents only 0.172% to 0.36% of transactions in large databases (Carcillo et al., 2021; Dornadula & Geetha, 2019). This requires specific techniques, such as resampling by oversampling or undersampling, to prevent the model from learning to classify everything as “legitimate”.

Another critical point is measuring success. Traditional metrics, such as accuracy, are ineffective in this context. The financial sector relies mainly on Recall, to avoid letting fraud escape, on Precision, to avoid blocking legitimate customers, on F1-Score and AUC-PR, which are suitable for imbalanced datasets (Kim et al., 2019).

In practice, detection involves hybrid systems. Automatic models perform real-time transaction scoring, while a human team analyzes only the most critical cases. Furthermore, ensembles that combine multiple models increase the stability and accuracy of the results (Khalid et al., 2024; Randhawa et al., 2018).

The Future of prevention

Two emerging trends point to the next generation of financial security.

Digital twins: a virtual replica of each customer’s behavior allows simulating a transaction before authorizing it. If the digital twin identifies a significant deviation, the operation can be blocked preventively (Chatterjee et al., 2024).
Blockchain and federated learning: financial institutions can train models collaboratively, but without sharing sensitive data. Blockchain technology provides a secure and transparent ledger, while federated learning allows for training distributed models while preserving privacy (Chatterjee et al., 2024). This combination addresses a historical bottleneck in the sector: improving models without compromising confidentiality.

The detection of fraud has evolved from simple rule-based systems to solutions that integrate advanced AI, specialized neural networks, and graph structures. Nevertheless, the challenge remains in constant mutation, and the effectiveness of institutions will depend on the ability to integrate new approaches, continuously update models, and combine automation with human analysis.

In the end, security is not a destination, but a continuous process of adaptation. And, in the technological race against financial crime, the winner is the one who evolves non-stop.

Who wrote this column

José Erasmo Silva

José Erasmo Silva é professor, formado em Matemática e Administração, com mais de 25 anos de experiência em gestão empresarial e de pessoas. É mestre e doutor em Administração, com foco em Finanças, e especialista em Data Science e Analytics e em Finanças e Controladoria. Realizou pós-doutorado na Universidade Federal da Bahia (UFBA). Atualmente, atua como professor orientador no MBA em Data Science, Inteligência Artificial e Analytics da USP/Esalq e leciona na EEP/FUMEP e na rede estadual de ensino de São Paulo.

You may also like

November 17, 2026

Detection and Diagnosis of Diseases in Corn and Rice in Mozambique with Deep Learning

Mozambican agriculture depends on corn and rice, fundamental crops for food security, but their productivity is strongly affected by phytosanitary diseases, whose early and accurate identification remains a challenge in resource-limited contexts. The study aimed to develop and compare Deep Learning-based models for the automatic detection and diagnosis of diseases in corn and rice leaves in Mozambique. Three approaches were used: a classic Convolutional Neural Network (CNN) developed from scratch, and two transfer learning models, ResNet50 and MobileNetV2. The dataset consisted of images from public databases and collected in the field, which underwent cleaning, balancing, and artificial augmentation steps. The models were trained and evaluated with standard performance metrics, including accuracy, precision, recall, F1-score, Log Loss, and Cohen’s Kappa. The classic CNN presented the best overall performance, with 94% precision, recall, and F1-score, and 93% accuracy and Cohen’s Kappa. MobileNetV2 achieved 91% F1-score and 90% accuracy, standing out for its lower Log Loss (0.30) and training time (6h32min59s). ResNet50 reached 80% F1-score and 79% accuracy. It was concluded that Deep Learning techniques have high potential to support phytopathological diagnosis in real agricultural contexts, contributing to faster and more accurate decisions in the management of corn and rice diseases.

Keywords: Deep learning; Rice; Plant diseases; Corn; Computer vision.

November 17, 2026

Artificial intelligence in accounting operational routines and financial efficiency

The incorporation of Artificial Intelligence (AI) and automation tools has reconfigured the routines of Brazilian accounting offices, impacting productivity, error mitigation, and financial efficiency. These impacts were analyzed in a small accounting firm, specialized in serving service providers in the medical field in São Caetano do Sul, São Paulo. The research adopted a qualitative approach, with a single case study design and incorporated units of analysis. Data were collected through a structured questionnaire, applied via Google Forms between January and February 2026, to five professionals in the operational structure of the firm in a census survey. The treatment followed content analysis with a priori and emergent categories. All respondents declared the use of automated tools or tools with AI resources. The perception of reduced execution time, decreased operational errors, rework, and better use of the team’s time converged in 80% of affirmative responses and 20% partial responses. The most benefited activities were bank reconciliation, import of fiscal documents, and tax assessment, with visible gains on typing errors, duplicate entries, and incorrect classification. Human intervention remained indispensable in tax planning, scenario analysis, and verification of ancillary obligations. The overall evaluation of AI’s contribution was predominantly favorable, with moderation linked to the complexity of fiscal regulations.

Keywords: Content analysis; Process automation; Accounting 4.0; Small business; Digital transformation.

November 17, 2026

Factors influencing schedule management in sewage treatment plant “retrofit” projects

Projects involving “retrofit” in Sewage Treatment Plants (STP) are characterized by high complexity, operational restrictions, and multiple technical interfaces. The study analyzed the perception of the professionals involved regarding the management and adherence to deadlines in “retrofit” projects for sewage treatment plants, considering technical, operational, and organizational factors. The research was characterized as an applied study, with a quali-quantitative approach, designed as a field survey. Data analysis was performed using descriptive statistics and qualitative categorization, employing SWOT, risk matrix (Probability x Impact), and 5W2H action plan tools. The results indicated a high perception of clarity (77.8%) and realism of deadlines (100% agreement), evidencing consistent initial planning. However, 77.7% of respondents pointed out that rework and scope changes directly impacted deadline adherence. The integration between engineering, manufacturing, and Production Planning and Control (PPC) showed an intermediate evaluation (77.7% partial/total agreement), indicating fragility in interfunctional coordination. The risk matrix highlighted as critical: scope changes, operational limitations of the STP, and technical complexity, all with a high level. As a central improvement, the standardization of scope change control, analysis, and approval was proposed, aiming to reduce rework and increase schedule predictability.

Keywords: Performance; Integration; Planning; Rework; Risk.

November 17, 2026

B2C Acquisition in diagnostic medicine: strategic partnerships with specialized medical offices

The diagnostic medicine sector in Brazil operates with high dependence on health plan providers, which limits the financial autonomy of service providers. This study proposed and analyzed a direct patient acquisition model (B2C) for a highly complex diagnostic medicine institution, structured through partnerships with Oncology and Cardiology practices and operationalized by a personalized customer service called concierge. The investigation adopted a mixed-methods approach in three phases: a field survey with a structured questionnaire applied to 87 patients, mapping of the operational flow using “Service Blueprint”, and analysis of the conversion rate from 312 medical referrals registered in the pilot project. The results indicated that trust in medical referral achieved 92.0% agreement, establishing itself as the main factor for adherence. The convenience of performing the exam on the same day reached 78.2%, and the willingness to pay directly was 55.2%, with polarization associated with the predominance of health plan users. The “Service Blueprint” identified three critical points in the transitions between stages of the patient journey. The overall conversion rate was 51.0%, with superior performance in Oncology (58.2%) compared to Cardiology (45.0%), and the greatest loss was concentrated in the acceptance and scheduling stage (28.3%). It was concluded that the model demonstrated possible operational viability and indications of patient acceptance, conditioned by price transparency and a reduction in the interval between consultation and approach by the concierge.

Keywords: Direct payment; Patient journey; Supplementary health; Concierge service; Conversion rate.

November 17, 2026

The role of the school manager in promoting an inclusive culture: leadership and educational policies

The research analyzed the school manager’s performance in promoting an inclusive culture, considering the need to transform legal guidelines and pedagogical foundations into effective institutional practices. It was assumed that school inclusion requires planning, organization, and strategic leadership in the school’s daily operations. A qualitative approach of an applied nature was adopted, developed in three complementary stages: documentary analysis of Brazilian legislation on inclusive education, bibliographic review on school leadership and management, and data systematization using management tools such as SWOT analysis and the PDCA cycle. The results indicated that the school management’s performance directly influenced the consolidation of inclusive environments, especially in the organization of processes, continuous team training, and strengthening of a collaborative institutional culture respectful of diversity. Structural, pedagogical, and relational challenges that demanded planned interventions were also identified. Finally, a Practical Guide for School Managers was developed, with guidelines, protocols, and operational orientations for decision-making and the organization of inclusive processes. It was concluded that the construction of an inclusive culture depended on the management’s ability to articulate public policies, pedagogical practices, and institutional processes, consolidating inclusion as a permanent commitment in the school context.

Keywords: educational accessibility; educational equity; participatory management; strategic planning; institutional processes.

November 17, 2026

An AI artifact based on Design Thinking to support the elicitation of software requirements from user needs

The development of software oriented to user needs frequently faces challenges in requirements elicitation, stemming from ambiguities in natural language and communication failures. Given this, an intelligent artifact integrating Design Thinking and Artificial Intelligence was proposed and validated, focusing on the Empathy and Definition stages, to support the collection, interpretation, and structuring of user needs. The research, of an applied, qualitative, and exploratory nature, conducted a Proof of Concept in a controlled environment, employing hypothetical scenarios. The artifact operated through guided natural language interviews, organizing information into elements such as pain points, context, and impact, and generating traceable problem syntheses. The results indicated that the system organized unstructured reports, reduced ambiguities, and preserved the meaning of the original information in most cases. The ability to reorganize logically in complex scenarios was also observed, although with limitations in separating multiple problems and dependence on instructions. It was concluded that the artifact has potential as a support for requirements elicitation, improving the clarity and structuring of information, but requires supervision and contextual control.

Keywords: Design Thinking; Requirements Elicitation; Requirements Engineering; Artificial Intelligence; Natural Language Processing.

November 17, 2026

The Extinction of the Monophasic Tax System in the Pharmaceutical Industry in Light of the Tax Reform

The consumption Tax Reform, established by Constitutional Amendment No. 132/2023, introduced structural changes to the Brazilian tax system, with the replacement of the Social Integration Program (PIS) and the Social Security Financing Contribution (COFINS) by the Contribution on Goods and Services (CBS), in a dual Value Added Tax (VAT) model. The objective was to analyze the impacts of the extinction of the single-stage system on the pharmaceutical industry, in light of the new regulatory design and its economic and legal effects. A qualitative, exploratory research was conducted through a case study and documentary analysis of legislation and specialized doctrine. It was examined whether the end of the single-stage system would imply a relevant increase in the tax burden for the sector. The results indicated that, although the formal overcoming of the single-stage system has occurred, the material exemption of medicines has been preserved, mainly due to the application of reduced rates of 60% and, in certain cases, a zero rate of the Tax on Goods and Services (IBS) and CBS. The change in model may cause occasional variations in revenue collection, without characterizing a structural increase in the tax burden, tending towards neutrality over time. It was preliminarily concluded that the Tax Reform reorganized the taxation technique in the pharmaceutical industry, replacing a concentrated regime with more transparent exemption mechanisms. This approach proved compatible with the principles of neutrality, full non-cumulativeness, and fiscality, maintaining tax protection for essential medicines and aligning fiscal policy with the fundamental right to health.

Keywords: CBS; COFINS; IBS; Dual VAT; PIS.