This article defines the concepts used for the comparative case study of liquidity risk measurement for the Swedish bond market, presented in the second piece of a given series. The concepts of neural networks, back-propagation and numerical optimisation algorithms are outlined. This is followed by an introduction to SNN, which applies a scaled exponential linear function to address the common issue of overfitting. Lastly, a more basic logistic regression approach is presented as an alternative method.
Part I: An Introduction to Self-Normalizing Neural Networks
Machine learning applications have become more prominent in the financial industry in recent years. Our new article series is exploring the benefits and challenges of using self-normalising neural networks (SNNs) for calculating liquidity risk. The first piece of the series introduces the main concepts used in the investigative case study for the Swedish bond market.