We conduct evolutionary programming experiments to evolve artificial neural networks for forecast combination. Using stock price volatility forecast data we find evolved networks compare favorably with a naïve average combination, a least squares method, and a Kernel method on out-of-sample forecasting ability-the best evolved network showed strong superiority in statistical tests of encompassing. Further, we find that the result is not sensitive to the nature of the randomness inherent in the evolutionary optimization process.
We consider a model of financial contagion in a bipartite network of assets and banks recently introduced in the literature, and we study the effect of power law distributions of degree and balance-sheet size on the stability of the system. Relative to the benchmark case of banks with homogeneous degrees and balance-sheet sizes, we find that if banks have a power-law degree distribution the system becomes less robust with respect to the initial failure of a random bank, and that targeted shocks to the most specialised banks (i.e. banks with low degrees) or biggest banks increases the probability of observing a cascade of defaults. In contrast, we find that a power-law degree distribution for assets increases stability with respect to random shocks, but not with respect to targeted shocks. We also study how allocations of capital buffers between banks affects the system's stability, and we find that assigning capital to banks in relation to their level of diversification reduces the probability of observing cascades of defaults relative to size based allocations. Finally, we propose a non-capital based policy that improves the resilience of the system by introducing disassortative mixing between banks and assets.
In this paper, we study the consequences of diversification on financial stability and social welfare using an agent based model that couples the real economy and a financial system. We validate the model against its ability to reproduce several stylized facts reported in real economies. We find that the risk of an isolated bank failure (i.e. idiosyncratic risk) is decreasing with diversification. In contrast, the probability of joint failures (i.e. systemic risk) is increasing with diversification which results in more downturns in the real sector. Additionally, we find that the system displays a "robust yet fragile" behaviour particularly for low diversification. Moreover, we study the impact of introducing preferential attachment into the lending relationships between banks and firms. Finally, we show that a regulatory policy that promotes bank-firm credit transactions that reduce similarity between banks can improve financial stability whilst permitting diversification.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.