1131 papers
This paper proposes RI-CSCEM, a cost-sensitive semi-supervised Expectation-Maximization framework that assigns hard or soft pseudo-labels to rejected applicants in credit scoring, effectively mitigating sample selection bias and asymmetric misclassification costs to outperform accepted-only baselines on Lending Club data.
This study demonstrates that integrating alternative data, such as rent and utility payment histories, into machine learning credit assessment models significantly increases loan approval rates for the "credit-invisible" population without substantially raising default risks or compromising demographic fairness, thereby advancing financial inclusion.
This systematic mapping review identifies a persistent skills gap and high graduate unemployment in Indonesia driven by curriculum-labor market misalignment, regional disparities, and competency deficits in key sectors, while highlighting the potential of recent policy initiatives like MBKM to strengthen university-industry linkages despite the need for further empirical evaluation and multidimensional frameworks.
This study employs a multi-method framework combining quantile regression, nonlinear ARDL, and wavelet coherence to demonstrate that in Ghana (1980–2020), exchange rate pass-through and fiscal dominance exhibit significant asymmetry and heterogeneity, with currency depreciations and debt servicing exerting disproportionately stronger inflationary effects during high-inflation regimes and at distinct multi-year time horizons.
This paper proposes the Hybrid Intelligence Governance Audit Matrix (HIGAM), a context-sensitive four-layer framework designed to standardize ethical AI oversight in C-Suite decision-making, specifically addressing the lack of procedural standards in existing models and offering tailored adaptation mechanisms for Peru's regulatory and corporate landscape.
This study of rural Bihar reveals that willingness to pay for sustainable arsenic mitigation is driven more by socio-structural factors, economic feasibility, and institutional trust than by health awareness alone, suggesting that effective interventions must address affordability and governance credibility rather than relying solely on awareness campaigns.
This paper proposes a reproducible, three-module methodological framework linking carbon-price shocks to credit risk and interbank contagion, illustrated through stylized assumptions and benchmarked against existing literature to guide climate transition risk assessment within Peru's concentrated, resource-exposure banking sector.
This paper proposes an NLP-driven framework using FinBERT and social media sentiment analysis to enhance the detection of political instability's impact on Peruvian banking asset volatility, demonstrating that such models significantly outperform traditional statistical baselines and offering a cost-effective early-warning tool for regulators.
This study quantitatively analyzes the systemic contagion risks between DeFi RWA-tokenized ecosystems and traditional banking in Peru, revealing high correlation and liquidity vulnerabilities, and proposes a tiered regulatory framework involving the SBS, SUNAT, and INDECOPI to mitigate these risks while enhancing tax compliance and consumer protection.
This study demonstrates that while autonomous LLM pricing agents do not reliably collude under neutral instructions, a regulatory price cap can paradoxically act as a Schelling focal point that coordinates them to sustain collusive prices just below the ceiling.