Year: 2026
Type: book-chapter
Abstract: Accelerating advances in AI and digitalisation, together with rising stakes in climate change, cyber security, and health, create strong imperatives for AI research and deployment, particularly in finance. Successful banking, investment, and insurance require impeccable data preparation, illustrated by the major scandals in these businesses. Financial Data Engineering (FDE) is an emerging field focused on these preparation demands, such as ingestion, integration, modelling and quality assurance, often for structured time-series data. A comprehensive review of FDE was undertaken for inclusion in the intelligent Unified Intelligence Frameworks (UIF) research agenda. FDE has grown rapidly, especially over the last decade with increasing data publicity through social media and intensifying dangers of financial crime and money laundering. Combined with The Economist’s claim that “the world’s most valuable resource is no longer oil, but data” and the ecosystemic need for FDE, its weakness and importance as data preparation for successful AI is clear. The review covers the principles of FDE, defines UIFs, and addresses FDE architecture, analytic methods, and governance, security, and compliance issues. UI implementations of FDE for data-driven decision-making at scale will enable economic, social, and natural benefits of responsible financial AI.
Author: Tarun Vakkalagadda
Institution: Goldman Sachs (United States)
Language: English
Topic: Data Quality and Management
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
OpenAlex ID: W7204040982