Minimizing the Value-at-Risk of Loan Portfolio via Deep Neural Networks
This addresses risk management for investors in peer-to-peer lending, though it appears incremental as it applies neural networks to an existing financial optimization problem.
The paper tackles the problem of minimizing Value-at-Risk (VaR) in peer-to-peer loan portfolios by proposing two deep neural network models, DeNN and DSNN, which predict loan default probabilities and timing, resulting in significant reductions in portfolio VaRs at various confidence levels compared to benchmarks.
Risk management is a prominent issue in peer-to-peer lending. An investor may naturally reduce his risk exposure by diversifying instead of putting all his money on one loan. In that case, an investor may want to minimize the Value-at-Risk (VaR) or Conditional Value-at-Risk (CVaR) of his loan portfolio. We propose a low degree of freedom deep neural network model, DeNN, as well as a high degree of freedom model, DSNN, to tackle the problem. In particular, our models predict not only the default probability of a loan but also the time when it will default. The experiments demonstrate that both models can significantly reduce the portfolio VaRs at different confidence levels, compared to benchmarks. More interestingly, the low degree of freedom model, DeNN, outperforms DSNN in most scenarios.