PENGAPLIKASIAN DEEP REINFORCEMENT Q-LEARNING UNTUK PREDIKSI PERDAGANGAN VALAS OTOMATIS
DOI:
https://doi.org/10.59407/jrsit.v1i3.519Keywords:
Machine Learning, Prediksi Harga Valas, Perdagangan Otomatis, Deep Reinforcement LearningAbstract
Bursa valas, pasar finansial terbesar di dunia dengan transaksi harian $5 triliun USD, adalah tempat investor dan pedagang membeli, menjual, dan menukar mata uang asing. Menghadapi tantangan membuat keputusan perdagangan yang tepat, inovasi teknologi seperti machine learning menawarkan solusi. Khususnya, Deep Reinforcement Learning (DRL), yang telah menunjukkan keunggulan atas manusia dalam berbagai tugas, termasuk game, menjanjikan potensi revolusioner dalam perdagangan valas. Menggunakan algoritma Deep Q-Network (DQN) Learning, penelitian ini bertujuan untuk mengembangkan model yang dapat memaksimalkan keuntungan dan meminimalkan risiko dalam lingkungan perdagangan yang kompleks dan dinamis. Kami menerapkan Deep Q-network (DQN) dan Deep Recurrent Q-network (DRQN) untuk mengembangkan sistem perdagangan harian otomatis pada pasangan mata uang EURUSD, memanfaatkan data perdagangan harian sebagai indikator lingkungan. Dalam penelitian kami, kinerja agen DRL dibandingkan dengan model tradisional dan DQN acak, menunjukkan bahwa algoritma DQN kami mengungguli model standar, sementara DRQN lebih superior, memanfaatkan pola tersembunyi dalam data urutan waktu. Hasil ini menekankan potensi penggunaan machine learning untuk menciptakan sistem perdagangan valas yang efisien dan menghasilkan keuntungan jangka panjang secara konsisten, menggambarkan langkah maju signifikan dalam teknologi perdagangan.
Kata kunci: Machine Learning, Prediksi Harga Valas, Perdagangan Otomatis, Deep Reinforcement Learning
References
U. S. Shanthamallu and A. Spanias, “Introduction to Machine Learning,” Synth. Lect. Signal Process., pp. 1–8, 2022, doi: 10.1007/978-3-031-03758-0_1.
P. Treleaven, M. Galas, and V. Lalchand, “Algorithmic Trading Review,” Commun. ACM, vol. 56, no. 11, pp. 76–85, Nov. 2013, doi: 10.1145/2500117.
A. M. Andrew, “REINFORCEMENT LEARNING: AN INTRODUCTION by Richard S. Sutton and Andrew G. Barto, Adaptive Computation and Machine Learning series, MIT Press (Bradford Book), Cambridge, Mass., 1998, xviii + 322 pp, ISBN 0-262-19398-1, (hardback, £31.95).,” Robotica, vol. 17, no. 2, pp. 229–235, 1999, doi: DOI: 10.1017/S0263574799211174.
V. Mnih et al., “Playing Atari with Deep Reinforcement Learning,” pp. 1–9, 2013.
Z. Jiang and J. Liang, “Cryptocurrency portfolio management with deep reinforcement learning,” in 2017 Intelligent Systems Conference, IntelliSys 2017, 2018, vol. 2018-Janua, pp. 905–913. doi: 10.1109/IntelliSys.2017.8324237.
M. Hausknecht and P. Stone, “Deep Recurrent Q-Learning for Partially Observable MDPs,” 1997.
R. S. Sutton and A. G. Barto, Reinforcement learning: an introduction, Second edi. Cambridge, Massachusetts: The MIT Press, 2018.
J. Chen, “Forex - FX,” Investopedia, 2018. https://www.investopedia.com/terms/f/forex.asp (accessed Nov. 16, 2022).
J. Moody, M. Saffell, Y. Liao, and L. Wu, “Reinforcement Learning for Trading Systems and Portfolios: Immediate vs Future Rewards BT - Decision Technologies for Computational Finance: Proceedings of the fifth International Conference Computational Finance,” A.-P. N. Refenes, A. N. Burgess, and J. E. Moody, Eds. Boston, MA: Springer US, 1998, pp. 129–140. doi: 10.1007/978-1-4615-5625-1_10.
C. J. C. H. Watkins and P. Dayan, “Q-learning,” Mach. Learn., vol. 8, no. 3, pp. 279–292, 1992, doi: 10.1007/BF00992698.
K. Hornik, M. Stinchcombe, and H. White, “Multilayer feedforward networks are universal approximators,” Neural Networks, vol. 2, no. 5, pp. 359–366, 1989, doi: https://doi.org/10.1016/0893-6080(89)90020-8.
Y. Deng, F. Bao, Y. Kong, Z. Ren, and Q. Dai, “Deep Direct Reinforcement Learning for Financial Signal Representation and Trading,” IEEE Trans. Neural Networks Learn. Syst., vol. 28, no. 3, pp. 653–664, 2017, doi: 10.1109/TNNLS.2016.2522401.
M. J. Hausknecht and P. Stone, “Deep Reinforcement Learning in Parameterized Action Space,” CoRR, vol. abs/1511.0, 2015.
G. Lample and D. S. Chaplot, “Playing FPS Games with Deep Reinforcement Learning,” 2016.
V. Mnih et al., “Human-level control through deep reinforcement learning,” Nature, vol. 518, no. 7540, pp. 529–533, 2015, doi: 10.1038/nature14236.
