Will Big Data and AI Redefine Indonesia’s Financial Future?

Jurnal Bisnis dan Komunikasi Digital, Год журнала: 2025, Номер 2(2), С. 21 - 21

Опубликована: Фев. 14, 2025

The rapid integration of big data and artificial intelligence (AI) is fundamentally reshaping Indonesia’s financial sector, driving unprecedented efficiency, innovation, inclusion. As Southeast Asia’s largest digital economy, Indonesia has embraced fintech solutions that leverage predictive analytics, machine learning, automation to enhance risk management, streamline transactions, expand services previously underserved populations. This transformation aligns with global trends, yet it presents distinct regulatory, infrastructural, ethical challenges. Drawing from Schumpeter’s Innovation Theory, Information Asymmetry Transaction Cost Economics, this study explores how AI redefine operations, improve decision-making, reduce market inefficiencies in the Indonesian banking ecosystem. Utilizing a qualitative phenomenological approach, research synthesizes insights industry experts, regulatory bodies, analysts assess implications data-driven strategies. Findings reveal while optimizes assessment, fraud detection, customer segmentation, hurdles, cybersecurity risks, literacy gaps remain key barriers sustainable adoption. continues its trajectory toward data-centric infrastructure, balancing technological advancement prudence will be critical shaping an inclusive resilient future. contributes ongoing discourse on intersection digitalization, economic policy, deployment emerging markets.

Язык: Английский

---

Gerenciamento de risco de crédito por meio da utilização de aprendizado de máquina

Revista Catarinense da Ciência Contábil, Год журнала: 2025, Номер 24, С. e3526 - e3526

Опубликована: Фев. 18, 2025

O risco de crédito tem desempenhado um papel central em várias crises financeiras globais nas últimas três décadas. cenário financeiro, cada vez mais complexo e interconectado, faz com que o gerenciamento se torne fundamental para a estabilidade crescimento das instituições financeiras. Este estudo caso como objetivo analisar utilização aprendizado máquina, especificamente algoritmo Gradient Boosting Decision Tree (GBDT), modelo preditivo, combina variáveis não significantes utiliza as consultas aos bureaus na gestão pelo Banco BS2, intuito adquirir maior acurácia tomada decisões melhorias mitigação riscos. A métrica F1, utilizada parâmetro demonstrar precisão do modelo, comparada da Serasa, apresenta índice superior, 0,77. capacidade monitoramento contínuo oferecida por esse preditivo proporcionado ao desde 2022, uma visão tempo real saúde financeira sua base clientes, ajudando implementação políticas assertivas. taxa inadimplência Pessoa Jurídica registrada BCB-CADOC (2024), mostrado decrescente após novo baseado no GBDT. contribui promoção inovação competitividade financeiras, incentivando transparência fortalecendo confiança investidores, stakeholders reguladores, Central, adotar ferramentas Inteligência Artificial (IA) detectam precocemente riscos previnem sistêmicas.

---

Automated Ledger or Fintech Analytics Platform?

FinTech, Год журнала: 2025, Номер 4(2), С. 14 - 14

Опубликована: Апрель 2, 2025

Initially designed as an automated ledger tool, Excel swiftly evolved into a data analytics platform for financial analysts to execute intricate analyses. is so commonplace in the industry that many do not even consider it fintech tool. The transformation of from simple tool low-code machine learning (mL) traditional focus fintech. mL will let and quantitative analyses quickly evolve models use advanced techniques. interface lets build predictive models. This paper explores how has applications along with risks associated Excel’s new functionality.

Язык: Английский

---

Aplicação das técnicas de machine learning na categorização de despesas de fluxo de caixa: uma pesquisa-ação

Revista Inovação Projetos e Tecnologias, Год журнала: 2025, Номер 13(1), С. e27432 - e27432

Опубликована: Апрель 4, 2025

A gestão financeira desempenha um papel fundamental na estabilidade e no crescimento das empresas. categorização inadequada de despesas fluxo caixa pode acarretar consequências negativas, como relatórios financeiros imprecisos, dificuldades previsão do problemas identificação áreas com custos excessivos ou ineficientes (Silva Navarro & Valverde, 2023). O objetivo deste relato técnico é apresentar a aplicação uma ferramenta desenvolvida base em técnicas machine learning para resolver o problema da incorreta planilha empresa familiar alagoana setor varejista artigos armarinhos. método adotado foi pesquisa-ação, que, ambiente organizacional, busca frequentemente solucionar natureza técnica. Devido às inconsistências nas categorias atribuídas manualmente pelos funcionários, solução utilizando bibliotecas Python análise texto classificação dados. Modelos Regressão Logística Random Forest foram aplicados automatizar correção categorias. Como resultado, dessas permitiu melhora precisão despesas, alcançando acurácia 94% modelo Forest. Este estudo evidencia eficácia integração processos financeiros, demonstrando essas tecnologias podem contribuir maior eficiência, reduzindo erros otimizando empresarial.

---

Predicting Market Sensitivity: The Role of Board Structure in the Beta Coefficient of Software Companies on the NASDAQ Global Select Market

Maliye Finans Yazıları, Год журнала: 2025, Номер 123, С. 14 - 34

Опубликована: Апрель 1, 2025

This study examines how board structure influences market sensitivity, measured by Beta, in software companies listed on the NASDAQ Global Select Market. Focusing governance metrics such as size, meeting frequency, and executive compensation, research analyzes their impact Beta from 2014 to 2023. Machine learning models, including Decision Trees Bagging Classifiers, evaluate this relationship, using accuracy, precision, recall, F1 scores. Findings suggest that factors significantly affect offering valuable insights for corporate leaders investors managing firm risk volatile sectors like software.

Язык: Английский

---

AI integration in financial services: a systematic review of trends and regulatory challenges

Humanities and Social Sciences Communications, Год журнала: 2025, Номер 12(1)

Опубликована: Апрель 22, 2025

Язык: Английский

---

Credit Rating Model Based on Improved TabNet

Mathematics, Год журнала: 2025, Номер 13(9), С. 1473 - 1473

Опубликована: Апрель 30, 2025

Under the rapid evolution of financial technology, traditional credit risk management paradigms relying on expert experience and singular algorithmic architectures have proven inadequate in addressing complex decision-making demands arising from dynamically correlated multidimensional factors heterogeneous data fusion. This manuscript proposes an enhanced rating model based improved TabNet framework. First, Kaggle “Give Me Some Credit” dataset undergoes preprocessing, including balancing partitioning into training, testing, validation sets. Subsequently, architecture is refined through integration a multi-head attention mechanism to extract both global local feature representations. Bayesian optimization then employed accelerate hyperparameter selection automate parameter search for TabNet. To further enhance classification predictive performance, stacked ensemble learning approach implemented: serves as extractor, while XGBoost (Extreme Gradient Boosting), LightGBM (Light Boosting Machine), CatBoost (Categorical KNN (K-Nearest Neighbors), SVM (Support Vector Machine) are selected base learners first layer, with acting meta-learner second layer. The experimental results demonstrate that proposed TabNet-based outperforms benchmark models across multiple metrics, accuracy, precision, recall, F1-score, AUC (Area Curve), KS (Kolmogorov–Smirnov statistic).

Язык: Английский

---

Detecting Credit Risk in Egyptian Banks: Does Machine Learning Matter?

Ekonomika, Год журнала: 2025, Номер 104(2), С. 78 - 94

Опубликована: Май 14, 2025

This study aims to significantly enhance the predictive modeling of credit risk within Egypt’s banking sector, particularly by differentiating between retail and corporate risks categorizing banks into listed non-listed groups. By utilizing a comprehensive dataset from Middle Eastern countries spanning 2011 2023, research applies advanced machine learning techniques, including Random Forest algorithm, refine model.The novelty this lies in its detailed exploration determinants specific Egyptian providing valuable insights emerging economies. A distinction various types bank classifications is made. The findings reveal that bank-specific factors – such as asset size, operating efficiency, liquidity, income diversification, capital adequacy are more significant predictors than macroeconomic indicators. trend holds for both banks, thus highlighting importance internal metrics.Moreover, algorithm demonstrates high accuracy rate predicting exposures, which underscores effectiveness financial settings. analysis indicates variations other characteristics crucial influencing risks. These suggest prioritizing metrics could lead effective management strategies relying solely on external economic conditions.Ultimately, study’s model expected assessment capabilities, strengthening positions fostering growth region. bridging gap theoretical understanding practical application, offers novel perspective tailored unique context sector.

Язык: Английский

---

Forecasting credit risk using machine learning

Elsevier eBooks, Год журнала: 2025, Номер unknown

Опубликована: Янв. 1, 2025

Язык: Английский

---

Understanding Financial Risk Dynamics: Systematic Literature Review inquiry into Credit, Market, and Operational Risks

ATESTASI Jurnal Ilmiah Akuntansi, Год журнала: 2024, Номер 7(2), С. 1186 - 1213

Опубликована: Авг. 14, 2024

This research delves into the intricate dynamics of financial risks—specifically credit, market, and operational risks—within banking, investment, corporate sectors, with a focus on both global Indonesian contexts. By examining key factors contributing to credit risk, impact market volatility stability, risks associated digital transformation sector, study seeks offer comprehensive analysis that is theoretically robust practically relevant. employs qualitative systematic literature review (SLR) explore within focusing The SLR process includes formulating questions, identifying screening relevant from databases like Scopus Google Scholar, synthesizing findings themes: risk dynamics, volatility, in age, integrated management. provides management Indonesia perspectives. reveals digitalization has significant enhancing efficiency but also increasing vulnerability cybersecurity threats disruptions. underscores need for frameworks address technology-driven challenges. highlights importance improving disclosure transparency, which can positively influence Liquidity identified as having greater short-term stability than necessitating proactive liquidity strategies. Technological innovations finance are found correlate increased risks, including failures threats, must be carefully managed. examines platform-based financing models investment In Indonesia, banking sector faces distinct challenges due high concentration systemic shocks, well rapid transformation. emphasizes necessity institutions implement measures, maintain resilient IT infrastructure, utilize advanced monitoring tools these emerging risks. stresses adopting account interdependencies between globalized market.

Язык: Английский

---