Loading...
P. Lalitha is a Senior Assistant Professor in the Department of Computer Science and Engineering at Geethanjali College of Engineering and Technology, India. Her research interests include Artificial Intelligence, Explainable AI, Machine Learning, and data analytics.
Artificial Intelligence (AI) has emerged as a fundamental element of contemporary financial frameworks, facilitating astute decision-making in banking, insurance, investment management, credit evaluation, fraud detection, anti-money laundering (AML), and risk analysis. Although sophisticated Machine Learning (ML) and Deep Learning (DL) models attain exceptional predicted precision, numerous work as "black-box" mechanisms, complicating stakeholders' comprehension of the rationale behind their choices. This absence of transparency generates apprehensions about trust, accountability, equity, adherence to regulations, and the ethical implementation of AI. Explainable Artificial Intelligence (XAI) tackles these issues by offering clear, transparent, and comprehensible elucidations for decisions made by AI. XAI bolsters user trust, aids in regulatory adherence, enhances model verification, and promotes ethical AI use within financial organisations. This chapter elucidates the principles, framework, methodologies, applications, obstacles, and prospective research avenues of Explainable AI within cloud-enabled, IoT-driven, and digital financial environments.