2005/08/01 by Martin Neil, Norman Fenton, Manesh Tailor · 1 citation
Computer Science · Decision Sciences · Engineering · Mathematics · #Bayesian Modeling and Causal Inference #Data Quality and Management #Computer science #Bayesian network #Process (computing) #Reliability (semiconductor) #Bayesian probability #Perspective (graphical) #Causal model #Basel II #Operational risk #Machine learning #Data mining #Econometrics #Risk analysis (engineering) #Management science #Artificial intelligence #Risk management #Engineering #Mathematics #Statistics
paper · doi:10.1111/j.1539-6924.2005.00641.x
openalex publication_date 2005/08/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/06/25
This report describes the use of Bayesian networks (BNs) to model statistical loss distributions in financial operational risk scenarios. Its focus is on modeling "long" tail, or unexpected, loss events using mixtures of appropriate loss frequency and severity distributions where these mixtures are conditioned on causal variables that model the capability or effectiveness of the underlying controls process. The use of causal modeling is discussed from the perspective of exploiting local expertise about process reliability and formally connecting this knowledge to actual or hypothetical statistical phenomena resulting from the process. This brings the benefit of supplementing sparse data with expert judgment and transforming qualitative knowledge about the process into quantitative predictions. We conclude that BNs can help combine qualitative data from experts and quantitative data from historical loss databases in a principled way and as such they go some way in meeting the requirements of the draft Basel II Accord (Basel, 2004) for an advanced measurement approach (AMA).