Aiming at the problem of stock index prediction, constructing a time series stock correlation network based on the fundamentals and technology of stock index components, then using the depth map neural network to learn the hierarchical representation of stock correlation network, and obtaining the candidate prediction signal in an end-to-end way. The architecture composed of depth map neural network method and end-to-end strategy is called DIFFPOOL architecture. Taking the CSI 300 index as the research object, combining the DIFFPOOL architecture with softmax classifier, long-term and short-term memory neural network (LSTM), linear regression, and logical regression, respectively, and uses the sliding time window method to obtain the corresponding prediction accuracy of stock index. The accuracy of the combined model under the optimal parameters fluctuates in the interval [0.56, 0.62]. Ultimately, the first mock exam is based on the mean absolute error (MAE) and the root mean square error (RMSE). The regression models of DIFFPOOL and regression models are compared with LSTM, recurrent neural network (RNN), and back propagation neural network (BP). Compared with the single model, the MAE and RMSE of the combined model are smaller, 0.0061 and 0.0081, respectively. Experiments show that by aggregating the node attribute information of the stock association network hierarchically, we can dynamically capture the impact of different industry sectors on stock index price fluctuations and further improve prediction accuracy.

Xueyan Li. Research on Stock Index Prediction Based on Stock Correlation Network and Deep Learning. Academic Journal of Computing & Information Science (2023), Vol. 6, Issue 4: 26-33. https://doi.org/10.25236/AJCIS.2023.060404.

[1] Mantegna R N. HierarchicalStructure in Financial Markets [J]. The European PhysicalJournalB, 1999, 11(1): 193-197.

[2] Miccich S, Bonannob G, Mantegna R N, et al. Degree stability of a minimum spanning tree of price return and volatility[J]. Physica A: Statistical Mechanics and its Applications, 2003, 324(1-2):66-73.

[3] Namaki A, Shirazi A H, Raei R, et al. Network analysis of a financial market based on genuine correlation and threshold method[J]. Physica A: Statistical Mechanics and its Applications, 2011, 390 21–22: 3835-3841.

[4] Tumminello M, Aste T, Di Matteo T, et al. A tool for filtering information in complex systems[J]. Proceedings of the National Academy of Sciences, 2005, 102 30: 10421-10426.

[5] Ying R, You J, Morris C, et al. Hierarchical graph representation learning with differentiable pooling [C]. Annual Conference on Neural Information Processing Systems NeurIPS, 2018, 4805-4815.

[6] Wu Z, Pan S, Chen F, et al. A Comprehensive Survey on Graph Neural Networks [J]. IEEE Transactions on Neural Networks and Learning Systems, 2021, 32(1): 4-24. 

[7] Zhou M, Xu W, Zhang W, et al. Leverage knowledge graph and GCN for fine-grained-level clickbait detection[J]. World Wide Web, 2022, 25(3):1243-1258. 

[8] Hamilton W L, Ying R, Leskovec J. Inductive representation learning on large graphs[C]. Annual Conference on Neural Information Processing Systems NeurIPS , 2017, 1024-1034

[9] Li Q, Tan J, Wang J, et al. A Multimodal Event-driven LSTM Model for Stock Prediction Using Online News [J]. IEEE Transactions on Knowledge and Data Engineering, 2020, PP (99):1-1.

[10] Dong-Ha, Shin, Kwang-Ho, choi, et al. Deep Learning Model for Prediction Rate Improvement of Stock Price Using RNN and LSTM[J]. The Journal of Korean Institute of Information Technology, 2017, 15(10):9-16.

[11] Zhang D, Lou S. The application research of neural network and BP algorithm in stock price pattern classification and prediction – ScienceDirect [J]. Future Generation Computer Systems, 2021, 115:872-879.

[12] Ghanbari M, Goldani M. Support Vector Regression Parameters Optimization using Golden Sine Algorithm and its application in stock market [J]. 2021.