Financial institutions manage operational risk (OpRisk) by carrying out activities required by regulation, such as collecting loss data, calculating capital requirements and reporting. For this purpose, for each OpRisk event, the loss amounts, dates, event types and descriptions and organizational units involved are recorded in OpRisk databases, and in recent years, OpRisk functions have been required to go beyond their regulatory tasks and to proactively manage OpRisk, preventing or mitigating its impact. As OpRisk databases contain, among other things, event descriptions, one area of opportunity is the extraction of information from such texts. This paper introduces a novel structured workflow for the application of text analysis techniques (one of the main natural language processing tasks) to OpRisk event descriptions in order to identify managerial clusters (which are more granular than regulatory categories) that cause the underlying risks. We complement and enrich the established framework of statistical methods based on quantitative data. Specifically, after delicate tasks such as data cleaning, text vectorization and semantic adjustment, we apply methods of dimensionality reduction and several algorithmic clustering models, and we compare their performance and weaknesses. Our results add to the knowledge of historical loss events and enable the mitigation of future risks.

Di Vincenzo, D., Greselin, F., Piacenza, F., Zitikis, R. (2023). A text analysis of operational risk loss descriptions. THE JOURNAL OF OPERATIONAL RISK, 18(3), 63-90 [10.21314/JOP.2023.003].

A text analysis of operational risk loss descriptions

Greselin, F;Piacenza, F
;
2023

Abstract

Financial institutions manage operational risk (OpRisk) by carrying out activities required by regulation, such as collecting loss data, calculating capital requirements and reporting. For this purpose, for each OpRisk event, the loss amounts, dates, event types and descriptions and organizational units involved are recorded in OpRisk databases, and in recent years, OpRisk functions have been required to go beyond their regulatory tasks and to proactively manage OpRisk, preventing or mitigating its impact. As OpRisk databases contain, among other things, event descriptions, one area of opportunity is the extraction of information from such texts. This paper introduces a novel structured workflow for the application of text analysis techniques (one of the main natural language processing tasks) to OpRisk event descriptions in order to identify managerial clusters (which are more granular than regulatory categories) that cause the underlying risks. We complement and enrich the established framework of statistical methods based on quantitative data. Specifically, after delicate tasks such as data cleaning, text vectorization and semantic adjustment, we apply methods of dimensionality reduction and several algorithmic clustering models, and we compare their performance and weaknesses. Our results add to the knowledge of historical loss events and enable the mitigation of future risks.
Articolo in rivista - Articolo scientifico
clustering; dimensionality reduction; natural language processing; operational risk; text analysis;
English
25-ago-2023
2023
18
3
63
90
reserved
Di Vincenzo, D., Greselin, F., Piacenza, F., Zitikis, R. (2023). A text analysis of operational risk loss descriptions. THE JOURNAL OF OPERATIONAL RISK, 18(3), 63-90 [10.21314/JOP.2023.003].
File in questo prodotto:
File Dimensione Formato  
Piacenza-2023-JOP-VoR.pdf

Solo gestori archivio

Descrizione: A text analysis of operational risk loss descriptions
Tipologia di allegato: Publisher’s Version (Version of Record, VoR)
Licenza: Tutti i diritti riservati
Dimensione 937.04 kB
Formato Adobe PDF
937.04 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10281/457898
Citazioni
  • Scopus 1
  • ???jsp.display-item.citation.isi??? 0
Social impact