Kripto Para Piyasaları için Yapay Zeka Tabanlı Tahmin Motorunun Geliştirilmesi

Öz

Bu çalışma, büyük veri analitiği ve gelişmiş yapay zeka algoritmaları kullanarak piyasa trendlerini ve fiyat dinamiklerini analiz etmeye, risk faktörlerini belirlemeye ve yatırımcılara tahminler sunmaya yardımcı olacak yenilikçi bir çözüm sunmayı amaçlamaktadır. Kısa, orta ve uzun vadeli Bitcoin kapanış fiyatı tahmin modelleri, Uzun-Kısa Vadeli Bellek (LSTM), Kapılı Tekrarlayan Birim (GRU) ve transformatör mimarisine dayalı modeller kullanılarak geliştirilmiş ve kısa vadeli Bitcoin kapanış fiyatı tahminleri için Monte Carlo senaryoları oluşturulmuştur; ayrıca Değer Riski (VaR) ve Koşullu Değer Riski (CVaR) gibi kuyruk riski metrikleri hesaplanmıştır. Binance API kullanılarak BTC/USDT sembolü için bir veri seti hazırlanmıştır. Geliştirilen modellerin performansı, Kök Ortalama Kare Hatası (RMSE), Ortalama Mutlak Hata (MAE) ve Ortalama Mutlak Yüzde Hatası (MAPE) kullanılarak değerlendirilmiştir. Sonuçlar, en başarılı sonuçların kısa vadeli tahmin modelleriyle elde edildiğini göstermiştir. GRU ile geliştirilen tahmin modelleri üstün performans göstermiştir.

Anahtar Kelimeler

• Kripto Para Piyasaları
• Bitcoin Kapanış Fiyatı Tahmini
• Makine Öğrenimi
• Transformer Mimarisi
• Risk Yönetimi ve Portföy Optimizasyonu

Development of an Artificial Intelligence-Based Prediction Engine for the Cryptocurrency Markets

Öz

This study aims to present an innovative solution that will help analyze market trends and price dynamics, identify risk factors, and provide investors with predictions using big data analytics and advanced artificial intelligence algorithms. Bitcoin closing price prediction models for short-term, medium-term, and long-term have been developed using Long-Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and transformer architecture based models and Monte Carlo scenarios have been generated for short-term Bitcoin closing price predictions; and tail-risk metrics such as Value at Risk (VaR) and Conditional Value at Risk (CVaR) have been calculated. A dataset for BTC/USDT symbol has been prepared using Binance API. The performance of developed models was evaluated using Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE). The results showed that most successful results have been obtained with prediction models developed for short term. Prediction models developed with GRU achieved superior performance.

Anahtar Kelimeler

• Cryptocurrency Markets
• Bitcoin Closing Price Prediction
• Machine Learning
• Transformer Architecture
• Risk Management and Portfolio Optimization

Kaynakça

1. 1. Almeida, J. & Gonçalves, T.C. (2023). A systematic literature review of investor behavior in the cryptocurrency markets. Journal of Behavioral and Experimental Finance, 37, 100785.
2. 2. Atree, M.K. & Tripathy, N. (2025). Cryptocurrency research: Bibliometric review and content analysis. International Review of Economics & Finance, 98, 103940.
3. 3. John, D.L., Binnewies, S. & Stantic, B. (2024). Cryptocurrency price prediction algorithms: A survey and future directions. Forecasting, 6(3), 637-671.
4. 4. Alnami, H., Mohzary, M., Assiri, B. & Zangoti, H. (2025). An integrated framework for cryptocurrency price forecasting and anomaly detection using machine learning. Applied Sciences, 15(4), 1864.
5. 5. Asmat, G. & Maiyama, K.M. (2025). Bitcoin price prediction using N-BEATs ML technique. EAI Endorsed Transactions on Scalable Information Systems, 12(2), 1-8.
6. 6. Kaur, R., Uppal, M., Gupta, D., Juneja, S., Arafat, S.Y., Rashid, J. & Alroobaea, R. (2025). Development of a cryptocurrency price prediction model: leveraging GRU and LSTM for Bitcoin, Litecoin and Ethereum. PeerJ Computer Science, 11, e2675.
7. 7. Makri, E., Palaiokrassas, G., Bouraga, S., Polychroniadou, A. & Tassiulas, L. (2025). Ethereum price prediction employing large language models for short-term and few-shot forecasting. arXiv preprint arXiv:2503.23190.
8. 8. Mazinani, A., Davoli, L. & Ferrari, G. (2025). Deep learning algorithms for cryptocurrency price prediction: A comparative analysis. Distributed Ledger Technologies: Research and Practice, 4(1), 1-38.

9. 9. Pandey, P. & Sharma, G. (2025). Effective price prediction of cryptocurrencies using CNN-based dual directional model. Science & Technology Asia, 201-219.
10. 10. Kang, M., Hong, J. & Kim, S. (2025). Harnessing technical indicators with deep learning based price forecasting for cryptocurrency trading. Physica A: Statistical Mechanics and its Applications, 660, 130359.
11. 11. Saeed, N., Shafi, I., Pervez, S., Thompson, E.B., Castilla, A.K., Samad, M.A. & Ashraf, I. (2025). Intelligent decision making for commodities price prediction: Opportunities, challenges and future avenues. Computational Economics, 1-59.
12. 12. Chandra, D., Tyagi, P., Gupta, R.S., Saxena, A.M. & Kharaliya, S. (2024). Cryptocurrency price prediction using machine learning. In 2024 2nd International Conference on Advancement in Computation & Computer Technologies (InCACCT), IEEE, 258-264.
13. 13. Golnari, A., Komeili, M.H. & Azizi, Z. (2024). Probabilistic deep learning and transfer learning for robust cryptocurrency price prediction. Expert Systems with Applications, 255, 124404.
14. 14. Kamboj, R., Jindal, A., Dubey, K. & Luthra, M. (2024). Cryptocurrency price prediction using machine learning. In 2024 4th Asian Conference on Innovation in Technology (ASIANCON), IEEE, 1-5.
15. 15. Kavithra, S., Girishankar, V.P., Iniyan, G. & Logesh, B. (2024). Cryptocurrency price prediction through integrated forecasting techniques. In 2024 3rd International Conference on Artificial Intelligence For Internet of Things (AIIoT), IEEE, 1-6.
16. 16. Kawli, D.P., Chaudhari, A.S., Ingale, P.D., Telange, G.A. & Banik, A. (2024). Cryptocurrency price prediction using machine learning. Asian Journal For Convergence in Technology (AJCT), 10(1), 19-23.
17. 17. Rajaei, M. & Mahmoud, Q.H. (2024). A prediction model for short price jump in cryptocurrency market. In 2024 IEEE 14th Annual Computing and Communication Workshop and Conference (CCWC), IEEE, 0144-0150.
18. 18. Özbek, A. (2022). Daily sea water temperature forecasting using machine learning approaches. Cukurova University, Journal of the Faculty of Engineering, 37(2), 307-318.
19. 19. Chen, X. & Long, Z. (2023). E-commerce enterprises financial risk prediction based on FA-PSO-LSTM neural network deep learning model. Sustainability, 15(7), 5882.
20. 20. Uluocak, İ. (2025). Comparative study of emission prediction using deep learning models. Cukurova University, Journal of the Faculty of Engineering, 40(2), 337-346.
21. 21. Basavarajaiah, S. & Garudachar, R. (2024). Prediction of global ionospheric TEC using attention based bidirectional long short-term memory and gated recurrent unit. Bulletin of Electrical Engineering and Informatics, 13(4), 2797-2808.
22. 22. Mozaffari, L. & Zhang, J. (2024). Predictive modeling of stock prices using transformer model. In Proceedings of the 2024 9th International Conference on Machine Learning Technologies, 41-48.