Exploring the Role of Explainable AI in Compliance Models for Fraud Prevention

International Journal of Latest Technology in Engineering Management & Applied Science, Journal Year: 2024, Volume and Issue: 13(5), P. 232 - 239

Published: June 27, 2024

Integration of explainable Artificial Intelligence (XAI) methodologies into compliance frameworks represents a considerable potential for augmenting fraud prevention strategies across diverse sectors. This paper explores the role AI in models prevention. In highly regulated sectors like finance, healthcare, and cybersecurity, XAI helps identify abnormal behaviour ensure regulatory by offering visible comprehensible insights AI-driven decision-making processes. The findings indicate extent to which can improve efficacy, interpretability, transparency initiatives aimed at preventing fraud. Stakeholders comprehend judgements made AI, spot fraudulent tendencies, rank risk-reduction tactics using methodologies. addition, it also emphasizes how crucial interdisciplinary collaboration is advancement its incorporation detection multiple conclusion, plays vital Therefore, through utilization transparent interpretable tools, entities strengthen their ability withstand operations, build trust among stakeholders, maintain principles within evolving systems.

Language: Английский

---

On the Explainability of Financial Robo-Advice Systems

Communications in computer and information science, Journal Year: 2024, Volume and Issue: unknown, P. 219 - 242

Published: Jan. 1, 2024

Language: Английский

---

AFTEA Framework for Supporting Dynamic Autonomous Driving Situation

Electronics, Journal Year: 2024, Volume and Issue: 13(17), P. 3535 - 3535

Published: Sept. 6, 2024

The accelerated development of AI technology has brought about revolutionary changes in various fields society. Recently, it been emphasized that fairness, accountability, transparency, and explainability (FATE) should be considered to support the reliability validity AI-based decision-making. However, case autonomous driving technology, which is directly related human life requires real-time adaptation response risks real world, environmental adaptability must a more comprehensive converged manner. In order derive definitive evidence for each object convergent environment, necessary transparently collect provide types road environment information objects assistance construct adaptable situations by considering all uncertainties changing environment. This allows unbiased fair results based on flexible contextual understanding, even do not conform rules patterns, interactions dynamic are possible transparent, environmentally adaptive, fairness-based outcomes basis decision-making process clear interpretation decisions. All these processes enable vehicles draw reliable conclusions take responsibility their decisions situations. Therefore, this paper proposes an adaptability, explainability, accountability (AFTEA) framework build stable explains definition, role, necessity AFTEA artificial intelligence highlights its value when applied integrated into technology. with will establishment sustainable environments aims direction establishing system adapts real-world scenarios.

Language: Английский

---

Understanding the Landscape: A Review of Explainable AI in Healthcare Decision-Making

Research Square (Research Square), Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 16, 2024

Breast cancer remains a significant global health concern, impacting millions of women. Early and accurate diagnosis is crucial for improving treatment outcomes reducing mortality rates. Machine learning (ML) has emerged as powerful tool breast prediction, demonstrating its ability to identify complex patterns relationships in large datasets. This paves the way efficient collaboration between AI healthcare professionals. systematic review explores diverse machine-learning techniques employed diagnosis. We comprehensively analyse evaluate effectiveness various computational methodologies by synthesising findings from wide range peer-reviewed studies. Our analysis highlights substantial advancements achieved utilizing machine algorithms prediction. However, challenges remain harnessing full potential healthcare. These include need larger more datasets, effective incorporation imaging data, development interpretable models. While offers immense healthcare, ensuring transparency, interpretability, trust crucial, especially domains like research emphasizes importance Explainable (XAI) enhancing clinical decision-making building patients providers. advocate fostering interdisciplinary among researchers, medical professionals, ethicists, policymakers ensure responsible integration

Language: Английский

---

Truth Versus Deception

Published: Jan. 1, 2024

Language: Английский

---