Gerçek Zamanlı Duygu Analizi ve Derin Pekiştirmeli Öğrenme Kullanılarak Kripto Para Piyasalarında Risk ve Uyumun Stratejik Yönetim Perspektifiyle Ele Alınması

Abstract

Bu çalışma, gerçek zamanlı duygu analizi ve teknik göstergeleri entegre eden derin bir takviyeli öğrenme çerçevesi kullanarak kripto para piyasası için gelişmiş bir yönetim stratejisi geliştirmeyi amaçlamaktadır. Çalışma, alım satım performansını artırmanın ötesinde, karar alma süreçlerinin dinamik piyasa koşullarıyla uyumlu hale getirilmesini ve finansal risklerin proaktif bir şekilde ele alınmasını vurgulayarak yaklaşımını stratejik bir yönetim perspektifiyle çerçevelendirmektedir. Temel amaç, piyasa oynaklığı ve duygusal önyargıların neden olduğu kayıpları en aza indirirken alım satım kârlarını artırmaktır. Duyarlılık analizi, piyasa duyarlılığını pozitif, negatif veya nötr olarak sınıflandırmak için önceden eğitilmiş FinRL NLP modeli kullanılarak gerçekleştirilir. Binance API aracılığıyla elde edilen geçmiş piyasa verileri Python'da analiz edilir ve modeller PPO, A2C ve DQN algoritmaları kullanılarak eğitilir. Bu algoritmalar, duyarlılık ve teknik göstergeleri durum uzayına dahil eder. Sonuçlar, duyarlılık analizinin bütünleştirilmesinin belirsizlik altında karar verme etkinliğini artırdığını (özellikle A2C algoritması ile) ve geleneksel stratejilerden daha sağlam performans sağladığını göstermektedir. Bulgular, kripto para piyasaları gibi değişken ortamlarda daha iyi hizalanmış, uyarlanabilir yatırım kararlarını desteklemek için duygulara duyarlı makine öğrenimini stratejik risk yönetimiyle birleştirmenin değerini vurgulamaktadır.

Keywords

• Derin pekiştirmeli öğrenme
• Duygu analizi
• Kripto piyasaları
• Stratejik yönetim
• Stratejik uyum
• Risk Yönetimi

A Strategic Management Perspective on Risk and Alignment in Crypto Markets Using Deep Reinforcement Learning and Real-Time Sentiment Analysis

Abstract

This study aims to develop an advanced management strategy for the cryptocurrency market This study aims to develop an advanced management strategy for the cryptocurrency market using a deep reinforcement learning framework that integrates real-time sentiment analysis and technical indicators. Beyond improving trading performance, the study frames its approach within a strategic management perspective by emphasizing the alignment of decision-making processes with dynamic market conditions and the proactive handling of financial risks. The core objective is to enhance trading profits while minimizing losses caused by market volatility and emotional bias. Sentiment analysis is conducted using the pre-trained FinRL NLP model to classify market sentiment as positive, negative, or neutral. Historical market data obtained via the Binance API is analyzed in Python, and the models are trained using PPO, A2C, and DQN algorithms. These algorithms incorporate sentiment and technical indicators into the state space. Results show that integrating sentiment analysis improves the effectiveness of decision-making under uncertainty particularly with the A2C algorithm providing more robust performance than traditional strategies. The findings highlight the value of combining sentiment-aware machine learning with strategic risk management to support better-aligned, adaptive investment decisions in volatile environments such as cryptocurrency markets.

Keywords

• Deep reinforcement learning
• Sentiment analysis
• Crypto markets
• Strategic management
• Strategic alignment
• Risk Management

References

1. Aldridge, I., & Krawciw, S. (2017). Real-time risk: What investors should know about fintech, high-frequency trading, and flash crashes. Wiley. https://doi.org/10.1002/9781119319030
2. Al-Shabi, M. A. (2020). Evaluating the performance of the most important lexicons used for sentiment analysis and opinion mining. IJCSNS International Journal of Computer Science and Network Security, 20(1), 1–7.
3. Andersen, T. J., & Sax, J. (2020). Strategic risk management: A research overview. Journal of Business Research, 112, 231–244. https://doi.org/10.1016/j.jbusres.2019.05.007
4. Andersen, T. G., Bollerslev, T., & Meddahi, N. (2011). Realized volatility forecasting and market microstructure noise. Journal of Econometrics, 160(1), 220–234. https://doi.org/10.1016/j.jeconom.2010.03.032
5. Bharathi, S., & Geetha, A. (2017). Sentiment analysis for effective stock market prediction. International Journal of Intelligent Engineering and Systems, 10(3), 146–154. https://doi.org/10.22266/ijies2017.0630.16
6. Bollen, J., Mao, H., & Zeng, X. (2011). Twitter mood predicts the stock market. Journal of Computational Science, 2(1), 1–8. https://doi.org/10.1016/j.jocs.2010.12.007
7. Chandler, A. D., Jr. (1969). Strategy and structure: Chapters in the history of the American industrial enterprise. MIT Press.
8. Charpentier, A., Élie, R., & Remlinger, C. (2023). Reinforcement learning in economics and finance. Computational Economics, 62, 425–462. https://doi.org/10.1007/s10614-021-10119-4

9. Dang, C. N., Moreno-García, M. N., & De la Prieta, F. (2021). Hybrid deep learning models for sentiment analysis. Complexity, 2021, Article 9986920. https://doi.org/10.1155/2021/9986920
10. Deveikyte, J., Geman, H., Piccari, C., & Provetti, A. (2020). A sentiment analysis approach to the prediction of market volatility. arXiv. https://doi.org/10.48550/arXiv.2012.05906
11. Fang, F., Ventre, C., Basios, M., Kanthan, L., Martinez-Rego, D., Wu, F., & Li, L. (2022). Cryptocurrency trading: A comprehensive survey. Financial Innovation, 8(1), 1–59. https://doi.org/10.1186/s40854-021-00321-6
12. rigo, M. L., & Anderson, R. J. (2011). Strategic risk management: A foundation for improving enterprise risk management and governance. Journal of Corporate Accounting & Finance, 22(3), 81–88. https://doi.org/10.1002/jcaf.20677
13. Gilbert, E., & Karahalios, K. (2010). Widespread worry and the stock market. Proceedings of the Fourth International AAAI Conference on Weblogs and Social Media, 58–65. https://doi.org/10.1609/icwsm.v4i1.14023
14. Huang, W., & Zhou, J. (2020). Deep reinforcement learning in finance: Framework, applications, and open issues. Journal of Risk and Financial Management, 13(1), 15. https://doi.org/10.3390/jrfm13010015
15. Hiew, J. Z. G., Huang, X., Mou, H., Li, D., Wu, Q., & Xu, Y. (2019). BERT-based financial sentiment index and LSTM-based stock return predictability. arXiv. https://doi.org/10.48550/arXiv.1906.09024
16. Jiang, Z., Xu, D., & Liang, J. (2017). A deep reinforcement learning framework for the financial portfolio management problem. arXiv. https://doi.org/10.48550/arXiv.1706.10059
17. Kabbani, T., & Duman, E. (2022). Deep reinforcement learning approach for trading automation in the stock market. arXiv. https://doi.org/10.48550/arXiv.2208.07165
18. Koratamaddi, P., Wadhwani, K., Gupta, M., & Sanjeevi, S. G. (2021). A multi-agent reinforcement learning approach for stock portfolio allocation. Proceedings of the 8th ACM IKDD CODS and 26th COMAD, 133–141. https://doi.org/10.1145/3430984.3431045
19. Kochliaridis, V., Kouloumpris, E., & Vlahavas, I. (2023). Combining deep reinforcement learning with technical analysis and trend monitoring on cryptocurrency markets. Neural Computing and Applications, 35, 21445–21462. https://doi.org/10.1007/s00521-023-08516-x
20. Liew, J. K. S., & Budavári, T. (2017). The “sixth” factor: A social media factor derived directly from tweet sentiments. The Journal of Portfolio Management, 43(3), 102–111. https://doi.org/10.3905/jpm.2017.43.3.102
21. Lillicrap, T. P., Hunt, J. J., Pritzel, A., Heess, N., Erez, T., Tassa, Y., Silver, D., & Wierstra, D. (2015). Continuous control with deep reinforcement learning. arXiv. https://doi.org/10.48550/arXiv.1509.02971
22. López de Prado, M. (2018). Advances in financial machine learning (Chapter 1). In Advances in financial machine learning (pp. 1–61). Wiley. ISBN 978-1-119-48208-6
23. McConnell, P. J. (2015). Strategic risk management: A tale of two strategies (Research Paper No. 38). SSRN. https://ssrn.com/abstract=2559626
24. Mnih, V., Kavukcuoglu, K., Silver, D., et al. (2015). Human-level control through deep reinforcement learning. Nature, 518(7540), 529–533. https://doi.org/10.1038/nature14236
25. Mnih, V., Puigdomenèch Badia, A., Mirza, M., Graves, A., Harley, T., Lillicrap, T. P., Silver, D., & Kavukcuoglu, K. (2016). Asynchronous methods for deep reinforcement learning. In M. F. Balcan & K. Q. Weinberger (Ed.), Proceedings of the 33rd International Conference on Machine Learning (pp. 1928–1937). PMLR.
26. Raffin, A., Hill, A., Gleave, A., Kanervisto, A., Ernestus, M., & Dormann, N. (2021). Stable Baselines3: Reliable reinforcement learning implementations. Journal of Machine Learning Research, 22(268), 1–8.
27. Schulman, J., Wolski, F., Dhariwal, P., Radford, A., & Klimov, O. (2017). Proximal policy optimization algorithms. arXiv. https://doi.org/10.48550/arXiv.1707.06347
28. Stappen, L., Baird, A., Schumann, L., & Schuller, B. (2021). The multimodal sentiment analysis in car reviews (MuSe-CaR) dataset: Collection, insights and improvements. arXiv. https://doi.org/10.48550/arXiv.2101.06053
29. Silver, D., Schrittwieser, J., Simonyan, K., et al. (2017). Mastering chess and shogi by self-play with a general reinforcement learning algorithm. arXiv. https://doi.org/10.48550/arXiv.1712.01815
30. Wang, L., Zong, B., Liu, Y., Qin, C., Cheng, W., Yu, W., Zhang, X., Chen, H., & Fu, Y. (2021). Aspect-based sentiment classification via reinforcement learning. 2021 IEEE International Conference on Data Mining (ICDM), 1391–1396. https://doi.org/10.1109/ICDM51629.2021.00178
31. Zhang, Z., Zohren, S., & Roberts, S. (2020). Deep reinforcement learning for trading. The Journal of Financial Data Science, 2(2), 25–40. https://doi.org/10.3905/jfds.2020.1.030