Measuring Systematic Risk with Neural Network Factor Model

2018/09/13 by Jeonggyu Huh, Huh, Jeonggyu
Economics, Econometrics and Finance · #Computational Finance (q-fin.CP) #FOS: Economics and business #Statistical Finance (q-fin.ST) #q-fin.CP #q-fin.ST

paper · pdf · doi:10.48550/arxiv.1809.04925

16 pages, 5 figures, 3 tables

arxiv created 2018/09/13 · arxiv updated 2018/09/14

Abstract

In this paper, we measure systematic risk with a new nonparametric factor model, the neural network factor model. The suitable factors for systematic risk can be naturally found by inserting daily returns on a wide range of assets into the bottleneck network. The network-based model does not stick to a probabilistic structure unlike parametric factor models, and it does not need feature engineering because it selects notable features by itself. In addition, we compare performance between our model and the existing models using 20-year data of S&P 100 components. Although the new model can not outperform the best ones among the parametric factor models due to limitations of the variational inference, the estimation method used for this study, it is still noteworthy in that it achieves the performance as best the comparable models could without any prior knowledge.

Related

• Deep Risk Model: A Deep Learning Solution for Mining Latent Risk Factors to Improve Covariance Matrix Estimation
• Multilayer Perceptron Neural Network Models in Asset Pricing: An Empirical Study on Large-Cap US Stocks
• Neural Networks and Value at Risk
• NeuralFactors: A Novel Factor Learning Approach to Generative Modeling of Equities
• Deep Learning Based Residuals in Non-linear Factor Models: Precision Matrix Estimation of Returns with Low Signal-to-Noise Ratio