Technical paper/Data
The market generator
A generative neural network is proposed to create synthetic datasets that mantain the statistical properties of the original dataset
An advanced hybrid classification technique for credit risk evaluation
In this paper, the authors employ a hybrid approach to design a practical and effective CRE model based on a deep belief network (DBN) and the K-means method.
Risk data validation under BCBS 239
Based on a survey of twenty-nine major financial institutions, this paper aims to advise banks and other financial services firms on what is needed to get ready for and become compliant with BCBS 239, especially in the area of risk data validation.
A general framework for constructing bank risk data sets
This paper proposes a general framework for constructing bank risk data sets, which provides an integrated process from data sources to comprehensive risk data sets.
Identifying patterns in the bank–sector credit network of Spain
In this paper, the authors study the topological and structural properties of the bank–sector credit network of Spain over the period 1997–2007.
Does higher-frequency data always help to predict longer-horizon volatility?
This paper shows that realized conditional autocorrelation in return residuals is a strong predictor of the relative performance of different frequency models of volatility.
Real option valuation and equity markets
Many non-financial assets can be viewed as ‘real options’ linked to some underlying variable such as a commodity price. Here, Thomas Dawson and Jennifer Considine show that the stock price of a well-known electricity generating company is significantly…
Component proponents
Principal component analysis is a widely used technique in finance but can be problematic when different data sets are grouped together. Christophe Pérignon and Christophe Villa show how to resolve this problem using a technique from biology called…
Equity to credit pricing
Default models