Attention Based Dynamic Graph Learning Framework for Asset Pricing

Recent studies suggest that financial networks play an essential role in asset valuation and investment decisions. Unlike road networks, financial networks are neither given nor static, posing significant challenges in learning meaningful networks and promoting their applications in price prediction. In this paper, we first apply the attention mechanism to connect the "dots" (firms) and learn dynamic network structures among stocks over time. Next, the end-to-end graph neural networks pipeline diffuses and propagates the firms' accounting fundamentals into the learned networks and ultimately predicts stock future returns. The proposed model reduces the prediction errors by 6% compared to the state-of-the-art models. Our results are robust with different assessment measures. We also show that portfolios based on our model outperform the S&P-500 index by 34% in terms of Sharpe Ratio, suggesting that our model is better at capturing the dynamic inter-connection among firms and identifying stocks with fast recovery from major events. Further investigation on the learned networks reveals that the network structure aligns closely with the market conditions. Finally, with an ablation study, we investigate different alternative versions of our model and the contribution of each component.

[1]  Jingjing Xu,et al.  Modeling the Stock Relation with Graph Network for Overnight Stock Movement Prediction , 2020, IJCAI.

[2]  P. Sarlin,et al.  Bank networks from text: interrelations, centrality and determinants , 2014, SSRN Electronic Journal.

[3]  Stephen Michael Taylor,et al.  Graph theoretical representations of equity indices and their centrality measures , 2019, Quantitative Finance.

[4]  Qi Zhang,et al.  GSTNet: Global Spatial-Temporal Network for Traffic Flow Prediction , 2019, IJCAI.

[5]  Bryan T. Kelly,et al.  Autoencoder Asset Pricing Models , 2019, Journal of Econometrics.

[6]  Philip S. Yu,et al.  A Comprehensive Survey on Graph Neural Networks , 2019, IEEE Transactions on Neural Networks and Learning Systems.

[7]  B. Kelly,et al.  Empirical Asset Pricing Via Machine Learning , 2018, The Review of Financial Studies.

[8]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[9]  Fabrizio Lillo,et al.  Correlation, Hierarchies, and Networks in Financial Markets , 2008, 0809.4615.

[10]  Richard K. Crump,et al.  Regression Based Estimation of Dynamic Asset Pricing Models , 2014 .

[11]  J. Juneja.  Common factors, principal components analysis, and the term structure of interest rates , 2012 .

[12]  Ruslan Bikbov,et al.  No-Arbitrage Macroeconomic Determinants of the Yield Curve , 2006 .

[13]  Charu C. Aggarwal,et al.  Stock Price Prediction via Discovering Multi-Frequency Trading Patterns , 2017, KDD.

[14]  Dacheng Xiu,et al.  Taming the Factor Zoo: A Test of New Factors , 2020 .

[15]  B. Kelly,et al.  Characteristics Are Covariances: A Unified Model of Risk and Return , 2018, Journal of Financial Economics.

[16]  Dafang Zhang,et al.  Dynamic Spatial-Temporal Graph Convolutional Neural Networks for Traffic Forecasting , 2019, AAAI.

[17]  M. Elliott,et al.  Financial Networks and Contagion , 2014 .

[18]  Seong Eun Maeng,et al.  Effects of global financial crisis on network structure in a local stock market , 2014 .

[19]  Zhanxing Zhu,et al.  Spatio-temporal Graph Convolutional Neural Network: A Deep Learning Framework for Traffic Forecasting , 2017, IJCAI.

[20]  Natalia Gimelshein,et al.  PyTorch: An Imperative Style, High-Performance Deep Learning Library , 2019, NeurIPS.

[21]  Yoshua Bengio,et al.  Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , 2014, ArXiv.

[22]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[23]  Ning Feng,et al.  Attention Based Spatial-Temporal Graph Convolutional Networks for Traffic Flow Forecasting , 2019, AAAI.

[24]  Mike K. P. So,et al.  Impacts of the COVID-19 pandemic on financial market connectedness , 2020, Finance Research Letters.

[25]  L. C. G. Rogers,et al.  Failure and Rescue in an Interbank Network , 2011, Manag. Sci..

[26]  Xuesong Yan,et al.  Stock price prediction based on deep neural networks , 2019, Neural Computing and Applications.

[27]  Yiqun Liu,et al.  Temporal Relational Ranking for Stock Prediction , 2018, ACM Trans. Inf. Syst..

[28]  E. Fama,et al.  A Five-Factor Asset Pricing Model , 2014 .

[29]  Michael J. Watts,et al.  IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS Publication Information , 2020, IEEE Transactions on Neural Networks and Learning Systems.

[30]  Dacheng Tao,et al.  Multi-task Recurrent Neural Networks and Higher-order Markov Random Fields for Stock Price Movement Prediction: Multi-task RNN and Higer-order MRFs for Stock Price Classification , 2019, KDD.

[31]  A. H. Shirazi,et al.  Network analysis of a financial market based on genuine correlation and threshold method , 2011 .

[32]  Nicolas Chapados,et al.  N-BEATS: Neural basis expansion analysis for interpretable time series forecasting , 2019, ICLR.

[33]  Networks in Production: Asset Pricing Implications , 2018, The Journal of Finance.

[34]  Dantong Yu,et al.  Latent factor model for asset pricing , 2020 .

[35]  Rangan Gupta,et al.  Return connectedness across asset classes around the COVID-19 outbreak , 2020, International Review of Financial Analysis.

[36]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[37]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[38]  Jaewoo Kang,et al.  HATS: A Hierarchical Graph Attention Network for Stock Movement Prediction , 2019, ArXiv.

[39]  Qi Zhang,et al.  Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting , 2020, NeurIPS.

[40]  Xavier Bresson,et al.  Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering , 2016, NIPS.

[41]  D. K. Nguyen,et al.  Covid-19 pandemic and tail-dependency networks of financial assets , 2020, Finance Research Letters.

[42]  Tie-Yan Liu,et al.  Investment Behaviors Can Tell What Inside: Exploring Stock Intrinsic Properties for Stock Trend Prediction , 2019, KDD.

[43]  Cyrus Shahabi,et al.  Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting , 2017, ICLR.