This thesis investigates how private and public actors shape the evolution of the Basel Committee’s G-SIB standard. It assembles a corpus of consultation papers, final standards, and stakeholder letters for the 2011 and 2017–2018 rounds. Using NLP—topic modeling and domain-adapted sentiment analysis—it extracts salient themes and measures positions in a comparable way. It introduces a Composite Influence Index integrating alignment between proposals and outcomes, engagement intensity, technical contribution, and sentiment convergence, with robustness checks on weights and specifications. The thesis contributes a replicable framework to quantify influence in financial rule-making and a documented dataset for comparisons.
Questa tesi esamina come attori privati e pubblici contribuiscono all’evoluzione dello standard G-SIB del Comitato di Basilea, viene costruito un corpus di documenti composto da consultazioni, standard finali e lettere degli stakeholder relativi ai cicli 2011 e 2017–2018. Mediante tecniche di NLP: topic modeling e sentiment analysis adattata al dominio regolatorio, si estraggono i temi rilevanti e si misurano in modo comparabile le posizioni espresse. Si introduce un Composite Influence Index che combina allineamento tra proposte ed esiti, intensità di engagement, contributo tecnico e convergenza del sentiment, con verifiche di robustezza su pesi e specifiche. Il lavoro offre un approccio replicabile per quantificare l’influenza nel rule-making finanziario e un dataset documentato per diversi confronti.
Lobbies Influence in Banking Regulation: A Machine Learning Approach to the Consultation Process
GALANTINO, DARIO
2024/2025
Abstract
This thesis investigates how private and public actors shape the evolution of the Basel Committee’s G-SIB standard. It assembles a corpus of consultation papers, final standards, and stakeholder letters for the 2011 and 2017–2018 rounds. Using NLP—topic modeling and domain-adapted sentiment analysis—it extracts salient themes and measures positions in a comparable way. It introduces a Composite Influence Index integrating alignment between proposals and outcomes, engagement intensity, technical contribution, and sentiment convergence, with robustness checks on weights and specifications. The thesis contributes a replicable framework to quantify influence in financial rule-making and a documented dataset for comparisons.| File | Dimensione | Formato | |
|---|---|---|---|
|
Galantino_last_thesis (1).pdf
accesso aperto
Dimensione
1.68 MB
Formato
Adobe PDF
|
1.68 MB | Adobe PDF | Visualizza/Apri |
I documenti in UNITESI sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/20.500.14247/26745