Deep learning is a powerful tool, which is becoming increasingly popular in financial modeling. However, model validation requirements such as SR 11-7 pose a significant obstacle to the deployment of neural networks in a bank's production system. Their typically high number of (hyper-)parameters...

This paper proposes a new Dynamic Stochastic General Equilibrium (DSGE) model with credit frictions and a banking sector, which endogenizes loan-to-value (LTV) ratios of households and banks by expressing them as a function of systemic and idiosyncratic proxies for risk. Moreover, the model...

[Update: Within four weeks of the original publication of this research report, Risk Magazine reported in its 28th February 2012 issue story titled 'Goodbye VaR? Basel to Consider Other Risk Metrics': "A review of trading book capital rules, due to be launched in March by the Basel Committee on...

Cognitive biases lead entrepreneurs to overinvest in their own companies, over exposing themselves to idiosyncratic risk. Our novel theoretical model explains entrepreneurial under-diversification by measuring the amount of potential bias in entrepreneurs' portfolio allocations brought about by...

We use a DSGE model that generates endogenous movements in risk premia to examine the positive and normative implications of alternative monetary policy rules. As emphasized by the micro-finance literature, variation in risk arises because households face fixed costs of transferring cash across...

This paper examines the two-fund separation paradigm in the context of an infinite-horizon general equilibrium model with dynamically complete markets and heterogeneous consumers with time- and state-separable utility functions. With the exception of the dynamic structure, we maintain the...