About the Project
Project Highlights
Applying dynamic network analysis and text mining to FCA reports.
Uncovering dynamic relationships, key actors, and emerging themes in UK financial regulation.
Providing insights for stakeholders, aiding policy decisions, and enhancing industry transparency.
Project
-Develop a comprehensive extraction process to capture and pre-process the textual content from a diverse set of FCA reports, including market studies, thematic reviews, and policy statements.
-Utilize the extracted information to construct dynamic networks representing relationships between entities mentioned in the reports. Nodes may represent regulatory bodies, financial institutions, market sectors, or other relevant entities. Edges can signify connections, collaborations, or regulatory influences.
-Incorporate temporal aspects by analysing the evolution of networks over time. Examine how the relationships and network structures change in response to regulatory developments, policy shifts, and market dynamics reflected in the FCA reports.
-Apply text mining techniques, including natural language processing (NLP) and sentiment analysis, to extract key themes, sentiments, and topics from the textual content. Investigate how these textual insights correlate with network dynamics and regulatory trends.
-Implement community detection algorithms to identify clusters within the dynamic networks. Explore how regulatory entities and financial institutions form communities based on shared interests, regulatory scrutiny, or market segments.
-The primary dataset for this research will consist of a diverse collection of FCA reports spanning multiple years. These reports will be sourced from the official FCA website, covering various aspects of financial regulation, market studies, and thematic reviews.
-The challenges associated with this research include handling the large volume of textual data, ensuring accurate extraction of entities and relationships, addressing the dynamic nature of regulatory environments, and developing robust algorithms for community detection.
-The outcomes of this research will have implications for understanding the evolving relationships within the financial regulatory landscape. Applications include identifying influential regulatory bodies, predicting shifts in market sentiment, and providing insights to policymakers and financial institutions for proactive decision-making.
-By undertaking this research, we aim to contribute to the field of financial regulation by providing a nuanced understanding of the dynamic relationships and regulatory trends unveiled through the analysis of FCA reports.
Project enquiries to supervisor: Dr Zahra Rezaei Szrl3@leicester.ac.uk
General enquiries CMSpgr@le.ac.uk" rel="nofollow" target="_blank">CMSpgr@le.ac.uk