Stock Trend Prediction with Multi-granularity Data: A Contrastive Learning Approach with Adaptive Fusion

Stock trend prediction plays a crucial role in quantitative investing. Given the prediction task on a certain granularity (e.g., daily trend), a large portion of existing studies merely leverage market data of the same granularity (e.g., daily market data). In financial investment scenarios, however, there exist amounts of finer-grained information (e.g., high-frequency data) that contain more detailed investment signals beyond the original granularity data. This motivates us to investigate how to leverage multi-granularity market data to enhance the accuracy of stock trend prediction. Some straightforward methods, such as concatenating finer-grained data as features or fusing with a model based on finer-grained features, may not lead to more precise stock trend prediction due to some unique challenges. First, the inconsistency of granularity between the target trend and finer-grained data could substantially increase optimization difficulty, such as the relative sparsity of the target trend compared with higher dimensions of finer-grained features. Moreover, the continuously changing financial market state could result in varying efficacy of heterogeneous multi-granularity information, which consequently requires a dynamic approach for proper fusion among them. In this paper, we propose the Contrastive Multi-Granularity Learning Framework (CMLF) to address these challenges. Particularly, we first design two novel contrastive learning objectives at the pre-training stage to address the inconsistency issue by constructing additional self-supervised signals relying on the inherent character of stock data. We also design a gate mechanism based on market-aware technical indicators to fuse the multi-granularity features at each time step adaptively. Extensive experiments on three real-world datasets show significant improvements of our approach over the state-of-the-art baselines on stock trend prediction and profitability in real investing scenarios.

[1]  Le Wu,et al.  Explainable Fashion Recommendation: A Semantic Attribute Region Guided Approach , 2019, IJCAI.

[2]  Xiang Cheng,et al.  Hierarchical Complementary Attention Network for Predicting Stock Price Movements with News , 2018, CIKM.

[3]  Yoshua Bengio,et al.  Learning Speaker Representations with Mutual Information , 2018, INTERSPEECH.

[4]  Enhong Chen,et al.  Multi-Interactive Attention Network for Fine-grained Feature Learning in CTR Prediction , 2021, WSDM.

[5]  J. Murphy.  Technical Analysis of the Financial Markets , 1999 .

[6]  James R. Glass,et al.  Improved Speech Representations with Multi-Target Autoregressive Predictive Coding , 2020, ACL.

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

[8]  R. Leal,et al.  Maximum Drawdown , 2005 .

[9]  Xuanjing Huang,et al.  Incorporating Corporation Relationship via Graph Convolutional Neural Networks for Stock Price Prediction , 2018, CIKM.

[10]  Garrison W. Cottrell,et al.  A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction , 2017, IJCAI.

[11]  Zhang Xiong,et al.  AlphaStock: A Buying-Winners-and-Selling-Losers Investment Strategy using Interpretable Deep Reinforcement Attention Networks , 2019, KDD.

[12]  E. Fama.  EFFICIENT CAPITAL MARKETS: A REVIEW OF THEORY AND EMPIRICAL WORK* , 1970 .

[13]  Gang Wang,et al.  Modeling Local Dependence in Natural Language with Multi-channel Recurrent Neural Networks , 2018, AAAI.

[14]  Zhongyu Wei,et al.  Using External Knowledge for Financial Event Prediction Based on Graph Neural Networks , 2019, CIKM.

[15]  Stella X. Yu,et al.  Unsupervised Feature Learning via Non-parametric Instance Discrimination , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[16]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[17]  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.

[18]  Pietro Liò,et al.  Deep Graph Infomax , 2018, ICLR.

[19]  Ralph Linsker,et al.  Self-organization in a perceptual network , 1988, Computer.

[20]  Yang Zhang,et al.  AlphaStock , 2019, Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.

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

[22]  Steven Walczak,et al.  An Empirical Analysis of Data Requirements for Financial Forecasting with Neural Networks , 2001, J. Manag. Inf. Syst..

[23]  Yoshua Bengio,et al.  Mutual Information Neural Estimation , 2018, ICML.

[24]  Jiang Bian,et al.  REST: Relational Event-driven Stock Trend Forecasting , 2021, WWW.

[25]  Daoqiang Zhang,et al.  Investor-Imitator: A Framework for Trading Knowledge Extraction , 2018, KDD.

[26]  Maosong Sun,et al.  Enhancing Stock Movement Prediction with Adversarial Training , 2018, IJCAI.

[27]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[28]  Aderemi Oluyinka Adewumi,et al.  Comparison of ARIMA and Artificial Neural Networks Models for Stock Price Prediction , 2014, J. Appl. Math..

[29]  Wei Zhang,et al.  Hybrid Deep Sequential Modeling for Social Text-Driven Stock Prediction , 2018, CIKM.

[30]  Chris Gale,et al.  Technical Analysis of Stock Trends , 2012 .

[31]  Huajun Chen,et al.  Knowledge-Driven Stock Trend Prediction and Explanation via Temporal Convolutional Network , 2019, WWW.

[32]  R. Thaler,et al.  A Survey of Behavioral Finance , 2002 .

[33]  Shay B. Cohen,et al.  Stock Movement Prediction from Tweets and Historical Prices , 2018, ACL.

[34]  Qi Sun,et al.  Multi-scale Two-way Deep Neural Network for Stock Trend Prediction , 2020, IJCAI.

[35]  Tao Qin,et al.  Individualized Indicator for All: Stock-wise Technical Indicator Optimization with Stock Embedding , 2019, KDD.

[36]  Nitish Srivastava.  Unsupervised Learning of Visual Representations using Videos , 2015 .

[37]  Yoshua Bengio,et al.  Learning deep representations by mutual information estimation and maximization , 2018, ICLR.

[38]  Tao Lin,et al.  Hybrid Neural Networks for Learning the Trend in Time Series , 2017, IJCAI.

[39]  W. Sharpe.  The Sharpe Ratio , 1994 .

[40]  Enhong Chen,et al.  Learning from History and Present: Next-item Recommendation via Discriminatively Exploiting User Behaviors , 2018, KDD.

[41]  Oriol Vinyals,et al.  Representation Learning with Contrastive Predictive Coding , 2018, ArXiv.

[42]  Xiaotie Deng,et al.  Exploiting Topic based Twitter Sentiment for Stock Prediction , 2013, ACL.

[43]  Geoffrey E. Hinton,et al.  A Simple Framework for Contrastive Learning of Visual Representations , 2020, ICML.

[44]  Enhong Chen,et al.  Estimating Early Fundraising Performance of Innovations via Graph-based Market Environment Model , 2019, AAAI.

[45]  Junjie Wu,et al.  Multilevel Wavelet Decomposition Network for Interpretable Time Series Analysis , 2018, KDD.

[46]  Kaiming He,et al.  Momentum Contrast for Unsupervised Visual Representation Learning , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[47]  Thomas H. Goodwin,et al.  The Information Ratio , 1998 .

[48]  Julien Velcin,et al.  Sentiment analysis on social media for stock movement prediction , 2015, Expert Syst. Appl..