Zeynep Hilal KİLİMCİ, Anıl Berk ALTUNER

A novel deep reinforcement learning based stock price prediction using knowledge graph and community aware sentiments

Stock market prediction has been an important topic for investors, researchers, and analysts. Because it is affected by too many factors, stock market prediction is a difficult task to handle. In this study, we propose a novel method that is based on deep reinforcement learning methodologies for the prediction of stock prices using sentiments of community and knowledge graph. For this purpose, we firstly construct a social knowledge graph of users by analyzing relations between connections. After that, time series analysis of related stock and sentiment analysis is blended with deep reinforcement methodology. Turkish version of Bidirectional Encoder Representations from Transformers (BerTurk) is employed to analyze the sentiments of the users while deep Q-learning methodology is used for the deep reinforcement learning side of the proposed model to construct the deep Q-network. In order to demonstrate the effectiveness of the proposed model, Garanti Bank (GARAN), Akbank (AKBNK), Türkiye İş Bankası (ISCTR) stocks in Borsa İstanbul are used as a case study. Experiment results show that the proposed novel model achieves remarkable results for stock market prediction task.

PDF

___

[1] Leung MT, Daouk H, Chen AS. Forecasting stock indices: a comparison of classification and level estimation models. International Journal of forecasting 2000; 16 (2): 173-190.
[2] Kumar M, Thenmozhi M. Forecasting stock index movement: A comparison of support vector machines and random forest. In: 9th Capital Markets Conference; India, 2006. pp. 1-16.
[3] Abu-Mostafa YS, Atiya AF. Introduction to financial forecasting. Applied intelligence 1996; 6 (3): 205-213.
[4] Tan TZ, Quek C, Ng GS. Biological brain‐inspired genetic complementary learning for stock market and bank failure prediction. Computational Intelligence 2007; 23 (2): 236-261.
[5] Goonatilake R, Herath S. The volatility of the stock market and news. International Research Journal of Finance and Economics 2007; 3 (11): 53-65.
[6] Gabielkov M, Legout A. The complete picture of the Twitter social graph. In: 2012 ACM Conference on CoNEXT Workshop; Nice, France 2012: 19-20.
[7] Sutton RS, Barto AG. Reinforcement learning: An introduction. 2nd ed. Cambridge, MA: MIT press, 2018.
[8] Holcomb SD, Porter WK, Ault SV, Mao G, Wang J. Overview on deepmind and its alphago zero ai. In: 2018 International Conference on Big Data and Education; Hawaii, USA 2018:67-71.
[9] Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J et al. Human-level control through deep reinforcement learning. Nature 2015; 518 (7540): 529-533.
[10] Auer S, Bizer C, Kobilarov G, Lehmann J, Cyganiak R et al. DBpedia: A Nucleus for a web of open data. In: Asian Semantic Web Conference; Busan, Korea 2007: 722-735.
[11] Hu YJ, Lin SJ. Deep reinforcement learning for optimizing finance portfolio management. In: 2019 IEEE Amity International Conference on Artificial Intelligence; Dubai, UAE 2019: 14-20.
[12] Rundo F. Deep LSTM with reinforcement learning layer for financial trend prediction in FX high frequency trading systems. Applied Sciences 2019; 9 (20): 4460-4478.
[13] Ye Y, Pei H, Wang B, Chen PY, Zhu Y et al. Reinforcement-learning based portfolio management with augmented asset movement prediction states. In: 2020 AAAI Conference on Artificial Intelligence; New York, USA 2020: 1112-1119.
[14] Xiao C, Chen W. Trading the Twitter Sentiment with Reinforcement Learning. arXiv preprint arXiv:1801.02243, 2018.
[15] Li Y, Ni P, Chang V. Application of deep reinforcement learning in stock trading strategies and stock forecasting. Computing 2019; 102: 1305–1322.
[16] Koratamaddi P, Wadhwani K, Gupta M, Sanjeevi SG. Market sentiment-aware deep reinforcement learning approach for stock portfolio allocation. International Journal of Engineering Science and Technology 2021; 24 (4): 848-859.
[17] Chen L, Gao Q. Application of deep reinforcement learning on automated stock trading. In: 2019 IEEE 10th International Conference on Software Engineering and Service Science; Beijing, China 2019: 29-33.
[18] Nan A, Perumal A, Zaiane OR. Sentiment and knowledge based algorithmic trading with deep reinforcement learning. arXiv preprint arXiv:2001.09403, 2020.
[19] Tenney I, Das D, Pavlick E. BERT rediscovers the classical NLP pipeline. arXiv preprint arXiv:1905.05950, 2019. [20] Mnih V, Kavukcuoglu K, Silver D, Graves A, Antonoglou I et al. Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602, 2013.
[21] Van Hasselt V, Guez A, Silver D. Deep reinforcement learning with double q-learning. In: 2016 AAAI Conference on Artificial Intelligence; Arizona, USA 2016: 2094-2100.
[22] Wang Z, Schaul T, Hessel M, Hasselt H, Lanctot M et al. Dueling network architectures for deep reinforcement learning. In: In International Conference on Machine Learning; New York, USA 2016: 1995-2003.
[23] Kingma DP, Ba J. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.