Deep Direct Reinforcement Learning for Financial Signal Representation and Trading
The DOI matches its Crossref record; 50 of the 51 references it cites were found in a registry or an index.
Abstract
Can we train the computer to beat experienced traders for financial assert trading? In this paper, we try to address this challenge by introducing a recurrent deep neural network (NN) for real-time financial signal representation and trading. Our model is inspired by two biological-related learning concepts of deep learning (DL) and reinforcement learning (RL). In the framework, the DL part automatically senses the dynamic market condition for informative feature learning. Then, the RL module interacts with deep representations and makes trading decisions to accumulate the ultimate rewards in an unknown environment. The learning system is implemented in a complex NN that exhibits both the deep and recurrent structures. Hence, we propose a task-aware backpropagation through time method to cope with the gradient vanishing issue in deep training. The robustness of the neural system is verified on both the stock and the commodity future markets under broad testing conditions.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“In machinelearning systems, humans shape and reshape algorithms through their daily actions and interactions (Deng, Bao, Kong, Ren, & Dai, 2017).”
From Artificial Intelligence and Management: The Automation–Augmentation Paradox (2021) · cites this paper as Deng, Bao, Kong, Ren, & Dai, 2017
Citations
Cites
Human-level control through deep reinforcement learning
Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., Graves, A., Riedmiller, M., Fidjeland, A. K., Ostrovski, G., et al. (2015) · Nature · doi:10.1038/nature14236 · Cited by 30,357
Reinforcement Learning: An Introduction
Sutton, R. S., & Barto, A. G. (1998) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.1998.712192 · Cited by 27,225
Reinforcement Learning: An Introduction
(2005) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2004.842673 · Cited by 24,496
(1999) · Cited by 12,812
(1995) · Cited by 10,558
A neural substrate of prediction and reward
Schultz, W., Dayan, P., & Montague, P. R. (1997) · Science · doi:10.1126/science.275.5306.1593 · Cited by 9,388
Learning Deep Architectures for AI
Bengio, Y. (2009) · Foundations and Trends® in Machine Learning · doi:10.1561/2200000006 · Cited by 9,239
Speech recognition with deep recurrent neural networks
Graves, A., Mohamed, A.-R., & Hinton, G. (2013) · 2013 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2013.6638947 · Cited by 8,893 · cited 1×
“DL techniques have been witnessed in image categorization [26] and speech recognition [29].”
MethodLearning long-term dependencies with gradient descent is difficult
Bengio, Y., Simard, P., & Frasconi, P. (1994) · IEEE Transactions on Neural Networks · doi:10.1109/72.279181 · Cited by 8,542 · cited 1×
“When directly applying the BPTT, the gradient vanish on deep layers is not avoided in the fine-tuning step [41].”
MethodMarkov decision processes: Discrete stochastic dynamic programming
Hazeghi, K., & Puterman, M. L. (1995) · Journal of the American Statistical Association · doi:10.2307/2291177 · Cited by 8,037
Research works printed but not linked: 1
- prokhorov, 2001, Dynamical neural networks for control, A Field Guide to Dynamical Recurrent Networks
Cited by
Items 501–600 of 822
Sparse convolutional model with semantic expression for waste electrical appliances recognition
Han, H., Liu, Y., Li, F., & Du, Y. (2024) · Science China Technological Sciences · doi:10.1007/s11431-023-2650-x · Cited by 3
“In the actual re-cycling process of waste electrical appliances, the deep convolutional network component suffers from a lack of reliability in feature decision information, which hinders the ability of the model component to perform semantic expression [9–11].”
Forecasting Digital Asset Return: An Application of Machine Learning Model
Ciciretti, V., Pallotta, A., Lodh, S., Senyo, P. K., & Nandy, M. (2024) · International Journal of Finance & Economics · doi:10.1002/ijfe.3062 · Cited by 4
FinRL Contests: Data‐Driven Financial Reinforcement Learning Agents for Stock and Crypto Trading
Wang, K., Holzer, N., Xia, Z., Cao, Y., Gao, J., Walid, A., Xiao, K., & Yanglet, X.-Y. L. (2025) · Artificial Intelligence for Engineering · doi:10.1049/aie2.12004 · Cited by 12
Deep Learning in Risk Assessment
Fernandes, J. M., Bissaro, L. Z., Santos, F., & Carneiro, M. G. (2019) · doi:10.5753/eniac.2019.9358 · Cited by 3
“The authors of [Deng et al. 2016] introduced a recurrent deep neural network novel structure consisting of simultaneous environment sensing and recurrent decision making for the problem of online financial assert trading.”
BackgroundEvaluation of Technical Analysis Trading Rules in a Artificial Stock Market Environment
Leles, M. C. R., Pereira, M. V. L., Iquiapaza, R. A., Sbruzzi, E. F., & Nascimento, C. L. (2020) · IEEE Latin America Transactions · doi:10.1109/tla.2020.9387641 · Cited by 3
Intelligent Trader Model Based on Deep Reinforcement Learning
Han, D., Zhang, J., Zhou, Y., Liu, Q. F., & Yang, N. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-30952-7_2 · Cited by 3
Blind Decision Making: Reinforcement Learning with Delayed Observations
Agarwal, M., & Aggarwal, V. (2021) · Proceedings of the International Conference on Automated Planning and Scheduling · doi:10.1609/icaps.v31i1.15940 · Cited by 8
Convergence and Optimality of Policy Gradient Methods in Weakly Smooth Settings
Zhang, M. S., Erdogdu, M. A., & Garg, A. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i8.20891 · Cited by 7
Supplemented with reinforcement learning to improve the detection of passive remote sensing devices
Peng, H. J., & Guo, R. J. (2023) · Signal Processing · doi:10.1016/j.sigpro.2023.108977 · Cited by 3
End-to-End Learning of Speech 2D Feature-Trajectory for Prosthetic Hands
Jafarzadeh, M., & Tadesse, Y. T. (2020) · International Conference on Transdisciplinary AI (TransAI) · doi:10.1109/transai49837.2020.00010 · Cited by 4
Learning to Cope with Adversarial AttacksPreprint
Lee, X. Y., Havens, A., Chowdhary, G. V., & Sarkar, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.12061 · Cited by 6
“, 2018), finance (Deng et al., 2017), engineering (Lee et al.”
BackgroundAn End-to-End Deep RL Framework for Task Arrangement in Crowdsourcing PlatformsPreprint
Shan, C., Mamoulis, N., Cheng, R. C. K., Li, G., Li, X., & Qian, Y. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.01030 · Cited by 3
“Deep RL has experienced dramatic growth recently in multiple fields, such as games (AlphaGo) [20], [28], [30], robotics [9], natural language processing [21], computer vision [18], finance [7], computer systems [16], [19], [36] and recommender systems [37], [38].”
Fu, Y., Yu, Z., Zhang, Y., & Lin, Y. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.13091 · Cited by 10
“…AlphaGo and beating human video game players, have triggered tremendously increased enthu-siasm to develop and deploy DRL-powered intelligence into numerous real-world inference and control applications, including robotics [42, 22, 53], autonomous vehicles [83], fi-nance [15] and smart grids [19].”
BackgroundCan Deep Reinforcement Learning Solve the Portfolio Allocation Problem? (PhD Manuscript)Preprint
Benhamou, E. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4599800 · Cited by 3
Can Deep Reinforcement Learning Reliably Improve Dynamic Portfolio Allocation?Preprint
Gupta, R., Pandey, A., & Pandey, A. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5241923 · Cited by 3
Deep Reinforcement Learning for Finance and the Efficient Market HypothesisPreprint
Odermatt, L., Beqiraj, J., & Osterrieder, J. R. (2021) · SSRN Electronic Journal · doi:10.2139/ssrn.3865019 · Cited by 4
Sun, H., Bian, Y., Han, L., Zhu, P., Cheng, D., & Liang, Y.-Q. (2024) · International Conference on Information and Knowledge Management · doi:10.1145/3627673.3680039 · Cited by 4
“There have been numerous attempts, which combine the perceptual ability ofDLwiththedecision-making abilityofRL[5,16].”
Graph-Driven Insights: Enhancing Stock Market Prediction with Relational Temporal Dynamics
Jia, R., Yang, K., Cheng, D., Han, L., & Liang, Y. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10889271 · Cited by 2
“Early work typically used Recurrent Neural Networks (RNN) to predict the exact price movement of a stock from a time series formed by stock technical indicators [8], [28], [30].”
Hybrids of Reinforcement Learning and Evolutionary Computation in Finance: A Survey
Yadav, S., Ravi, V., & Kalyanakrishnan, S. (2025) · ACM Computing Surveys · doi:10.1145/3728634 · Cited by 4
Rapid Dynamical Pattern Classification via Deterministic Learning From Sampling Sequences
Wu, W., Li, Z., Sun, C., Wang, C., & Chen, G. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2025.3565535 · Cited by 2
Sharma, Y., Gupta, S., Gupta, N., Tiwari, E., Singh, R., Khanna, N. N., Al-Maini, M., Rathore, V., Ahluwalia, P., Kumari, V., et al. (2025) · Soft Computing · doi:10.1007/s00500-025-10901-8 · Cited by 3
Yunxiang, G., & Bangying, T. (2025) · Discover Artificial Intelligence · doi:10.1007/s44163-025-00547-8 · Cited by 2
“In terms of deep reinforcement learning applied to the study of financial portfolios, Deng [4] applied deep reinforcement learning to trading a single financial asset to construct a DDR trading system, which obtained reliable returns in the futures market.”
Modular Reinforcement Learning for Multi-Market Portfolio Optimization
Khemlichi, F., Khamlichi, Y. I., & Ali, S. E. B. (2025) · Information · doi:10.3390/info16110961 · Cited by 5
Deep Reinforcement Learning-Based Control of Snake Robot Joints
Baysal, Y. A., & Altaș, İ. H. (2025) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-025-10600-4 · Cited by 2
Predicting the Stock Price Using a Bayesian Graph Neural Networks-Based Architecture
Dang, Q.-V., & Nguyen, N.-S.-A. (2025) · Communications in computer and information science · doi:10.1007/978-981-95-4724-1_23 · Cited by 2
Li, L., Matt, P.-A., & Heumann, C. (2022) · Applied Intelligence · doi:10.1007/s10489-022-03280-2 · Cited by 2
“For instance, [17] embed a DL model into Direct RL for real-time financial trading.”
MethodMulti-Agent Uncertainty Sharing for Cooperative Multi-Agent Reinforcement Learning
Chen, H., Yang, G., Zhang, J., Yin, Q.-Y., & Huang, K.-Q. (2022) · IEEE International Joint Conference on Neural Network · doi:10.1109/ijcnn55064.2022.9891948 · Cited by 1
“With the goal to maximize the cumulative reward, the agents can learn to play video games [2], master the game of Go [3]–[5], complete quantitative trading [6], and realize robotic control [7]–[9].”
BackgroundAlsulaiman, T. (2024) · American Journal of Financial Technology and Innovation · doi:10.54536/ajfti.v2i1.2354 · Cited by 2
“2 (1) 1-14, 2024 AI-ML methods (LSTM, ANNT, RL, CF and GA) (Dash & Dash, 2016; Krauss et al ., 2017; Deng et al ., 2016; Gao & Chai, 2018; Yu & Yan, 2020; Al-Sulaiman, 2022; Lee et al ., 2019; Deng et al ., 2016; Almahdi & Yang, 2017; Jang & Lee, 2017; Al-Sulaiman & Al-Matouq, 2021; de Almeida et…”
InfluentialSantos, G. D., & Lima, K. R. (2024) · Anais do Simpósio Brasileiro de Sistemas de Informação (SBSI) · doi:10.1145/3658271.3658282 · Cited by 3
Chen, H., Xu, C., & Xu, Z. (2024) · Computational Economics · doi:10.1007/s10614-024-10786-z · Cited by 3
“(2) Temporal considerations and long-term impact: decisions made at present can influence future outcomes, underscoring the importance of considering temporal dynamics and long-term effects to avoid myopic behaviors and local optima (Deng et al., 2017).”
Reinforcement learning algorithms for continuous-time VWAP targeting execution
Zhou, X., Chen, W., & Xu, M. (2025) · Advances in Complex Systems · doi:10.1142/s1793962325500400 · Cited by 3
Dynamic Portfolio Return Classification Using Price-Aware Logistic Regression
Baguda, Y. S., Aljahdali, H. M., & Taha, A. A. (2025) · Mathematics · doi:10.3390/math13111885 · Cited by 2
Cryptocurrency Futures Portfolio Trading System Using Reinforcement Learning
Chun, J. H., & Lee, S. (2025) · Applied Sciences · doi:10.3390/app15179400 · Cited by 6
Wudenhe, A., & Tseng, H. (2021) · IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS) · doi:10.1109/ispass51385.2021.00048 · Cited by 4
“comprehension," arXiv, 2018. [30] T.-Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollar, ''Focal loss for dense object detection," in Proceedings of the IEEE International Conference on Computer Vision (ICCV), Oct 2017. [31] K. He, X. Zhang, S. Ren, and J. Sun, "Deep residnal learning for image recognition," CoRR, vo…”
InfluentialQuantum Trader—A Multiagent-Based Quantum Financial Forecast and Trading System
Lee, R. (2019) · Springer eBooks · doi:10.1007/978-981-32-9796-8_13 · Cited by 2
Baseline win rates for neural-network based trading algorithms
Krause, A., & Fairbank, M. (2020) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn48605.2020.9207649 · Cited by 2
“We have described how to empirically sample a baseline win rate for pure fixed-look ahead forecasting models (3), and for trading systems that use stop loss-orders (14).”
BackgroundLin, Y.-C., & Blum, J. J. (2020) · Spring Simulation Multiconference · doi:10.22360/springsim.2020.ais.002 · Cited by 1
“In addition to only using recurrent network as policy network to interpret data directly, other research has used deep fully connected networks and convolution neural networks (CNN) as feature transformation to improve agent performance (Deng et al. 2017, Jiang and Liang 2017).”
MethodOn the Predictability of the Equity Premium Using Deep Learning Techniques
Iworiso, J., & Vrontos, S. D. (2020) · The Journal of Financial Data Science · doi:10.3905/jfds.2020.1.051 · Cited by 3
Machine Learning and Cryptocurrency in the Financial Markets
Cho, H., Lee, K., & Kim, C. (2021) · Blockchain technologies · doi:10.1007/978-981-33-6137-9_13 · Cited by 4
Online Optimal Investment Portfolio Model Based on Deep Reinforcement Learning
Ni, G. A. O., He, Y., Jiao, Y., & CHANG, Z. (2021) · International Conference on Machine Learning and Computing (ICMLC) · doi:10.1145/3457682.3457685 · Cited by 2
“Deng et al. innovatively constructed a deep reinforcement learning algorithmic trading model, with Fuzzy learning, RNN neural network and RRL applied separately, in order to strengthen the model’s ability to perceive the environment [5].”
MethodRusso, A., & Proutière, A. (2022) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.23919/acc53348.2022.9867848 · Cited by 2
“This increased interest has made RL being applied more frequently in industrial applications, from temperature control in buildings [11], to health-care [51], financial trading [13] and more.”
Optimal Option Hedging with Policy Gradient
Xiao, B., Yao, W., & Zhou, X. (2021) · IEEE ... International Conference on Data Mining workshops · doi:10.1109/icdmw53433.2021.00145 · Cited by 6
Deep Reinforcement Learning Stock Trading Strategies Combining Trends
何, 祁. (2022) · Computer Science and Application · doi:10.12677/csa.2022.123068 · Cited by 2
Stock Market Prediction Based on Big Data Using Deep Reinforcement Long Short-Term Memory Model
Ishwarappa, K., & Anuradha, J. (2022) · International Journal of e-Collaboration · doi:10.4018/ijec.304445 · Cited by 2
Reinforcement Learning for Bipedal Gait with MAX-E2 Humanoid Robot
Yanguas-Rojas, D., Mojica‐Nava, E., & Cardenas, A. (2022) · International Journal of Humanoid Robotics · doi:10.1142/s0219843622500219 · Cited by 3
An Efficient Hardware Implementation of the Double Q-Learning Algorithm
Ben-Akka, M., Tanougast, C., Diou, C., & Chaddad, A. (2023) · International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME) · doi:10.1109/iceccme57830.2023.10252988 · Cited by 4
“Recently, the use of RL algorithm is becoming increasingly important in different fields such as telecommunication [3]- [4], power management [5], robotics [6]–[8], financial trading [9] and Internet of Things (IOT) [10].”
MethodTransforming the Financial Industry Through Machine and Deep Learning Innovations
Singh, S., Bhagat, R., Preeti, S. H., & Girish, G. P. (2023) · Lecture notes in networks and systems · doi:10.1007/978-3-031-36246-0_16 · Cited by 2
A Divide-and-Conquer Framework for Attention-based Combination of Multiple Investment Strategies
Yang, X., Liu, W., Wang, L., Qu, C., & Bian, J. (2019) · IEEE Global Conference on Signal and Information Processing · doi:10.1109/globalsip45357.2019.8969091 · Cited by 2
Latent Structure Matching for Knowledge Transfer in Reinforcement Learning
Zhou, Y., & Yang, F. (2020) · Future Internet · doi:10.3390/fi12020036 · Cited by 3
“In recent years, reinforcement learning has been successfully applied to some aspects of life such as medical care [4], finance [5], and transportation [6].”
BackgroundZhao, F., Zhang, Y., & Chen, H. (2017) · Pattern Recognition · doi:10.1016/j.patcog.2017.07.015 · Cited by 2
RetractedIntelligent Trainer for Model-Based Reinforcement LearningPreprint
Li, Y., Dong, L., Zhou, X., Wen, Y., & Guan, K. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.09496 · Cited by 2
“For example, in [16], a DRL agent is proposed to solve financial trading tasks; in [17], a neural RL agent is trained to mimic the human motor learning; in [18], an off-policy RL method is proposed to solve nonlinear nonzero-sum games.”
MethodA* Tree Search for Portfolio ManagementPreprint
Gao, X., Tu, S., & Xu, L. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.01855 · Cited by 4
“Since the trading environment is too complicated to be estimated in a discrete space, Q-leaning is not a good paradigm for trading[6, 18].”
Zhou, Y., Zhang, B., Xu, C., Lan, T., Diao, R., Shi, D., Wang, Z., & Lee, W. (2020) · arXiv (Cornell University) · Cited by 4
Demystifying Deep Neural Networks Through Interpretation: A SurveyPreprint
Dao, G., & Lee, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.07119 · Cited by 3
On CVaR-Based Reinforcement Learning in Quantitative InvestmentPreprint
Alameer, A., & Alshehri, K. A. (2022) · doi:10.36227/techrxiv.19961525.v1 · Cited by 2
Factor Investing with Reinforcement LearningPreprint
Coqueret, G., & André, E. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4103045 · Cited by 3
StockBench: Can LLM Agents Trade Stocks Profitably In Real-world Markets?
Chen, Y., Yao, Z., Liu, Y., Xin, A., Ye, J., Yu, J., Hou, L., & Li, J. (2025) · arXiv · Cited by 62
“In particular, we follow previous frameworks (Zhang et al., 2020; Tsantekidis et al., 2017; Moody and Saffell, 2001; Deng et al., 2016) and organize the stock-trading workflow into four essential stages: portfolio overview, in-depth stock analysis, decision generation, and execution and validation.”
Player-Guided AI outperforms standard AI in Sequence Alignment Puzzles
Mutalova, R., Sarrazin-Gendron, R., Ghasemloo Gheidari, P., Cai, E., Richard, G., Caisse, S., Knight, R., Blanchette, M., Szantner, A., & Waldispühl, J. (2023) · Proceedings of The ACM Collective Intelligence Conference · doi:10.1145/3582269.3615597 · Cited by 1
“The algorithm has also been extended to other domains, such as robotics [15] and finance [3], where it has shown promise in solving complex problems.”
Efficient Approach for Rhopalocera Classification Using Growing Convolutional Neural Network
Kaur, I., Goyal, L. M., Ghansiyal, A., & Hemanth, D. J. (2022) · International Journal of Uncertainty Fuzziness and Knowledge-Based Systems · doi:10.1142/s0218488522400189 · Cited by 1
Deep Reinforcement Learning for Tehran Stock Trading
Yousefi, N. (2022) · Journal of Novel Engineering Science and Technology · doi:10.56741/jnest.v1i02.171 · Cited by 1
“These kinds of value-based DRL are always applied to solve the optimization problems defined in discrete space [3].”
MethodPortfolio management algorithm based on long-term prediction of assets
Lei, M., Pan, X., Gao, S.-S., & Zhang, Y. (2022) · ICBDT · doi:10.1145/3565291.3565315 · Cited by 1
“Wu et al. [27] described a reinforcement learning based portfolio management system (PMS) that uses CNN and RNN as policy networks and incorporates a Sharpe ratio reward function to learn investment transactions.”
MethodInfluentialMalladhi, A. (2023) · International Journal of Science and Research (IJSR) · doi:10.21275/sr23426081726 · Cited by 2
Enhancing Financial Market Prediction with Reinforcement Learning and Ensemble Learning
Tran, D., Tran, Q. T. T., Tran, M., Nguyen, V., & Tran, M. (2024) · IFIP advances in information and communication technology · doi:10.1007/978-3-031-63215-0_3 · Cited by 1
Plasticity Driven Knowledge Transfer for Continual Deep Reinforcement Learning in Financial Trading
Katsikas, D., Passalis, N., & Tefas, A. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-78189-6_6 · Cited by 2
Pu, X., Liu, P., Kang, W., & Yu, C. (2024) · IEEE Access · doi:10.1109/access.2024.3522107 · Cited by 1
An Approach to the Finance Affair Through Reinforcement Learning
Shukla, N., Jaiswal, S., Chaudhri, C., Pinjarkar, L., Agrawal, P., & Kaur, G. (2024) · 2024 IEEE 6th International Conference on Cybernetics, Cognition and Machine Learning Applications (ICCCMLA) · doi:10.1109/icccmla63077.2024.10871473 · Cited by 1
“Yue Deng, et al. [11] provide a method for task-aware reverse propagation through time to deal with the gradient vanishing issue in deep learning.”
Yuxiaoyuan, Peng, W., & Haron, N. A. (2025) · IEEE Access · doi:10.1109/access.2025.3558887 · Cited by 2
“Notable innovations include deep reinforcement learning approaches that can effectively capture complex market dynamics and temporal dependencies [78], [79].”
GA-PRE: A Genetic Algorithm-Based Automatic Data Preprocessing Algorithm
Jiao, J., & Yuan, L. (2025) · Genetic and Evolutionary Computation Conference (GECCO) · doi:10.1145/3712256.3726312 · Cited by 1
“The development and application of these technologies, especially in fields such as medical diagnosis[13], financial analysis[3], and politics[17], have demonstrated tremendous potential and value.”
APPLICATION OF MATHEMATICAL MODELING IN FINANCE: A REVIEW
Dawi, N. M., Singh, A. K., & Namazi, H. (2025) · Fractals · doi:10.1142/s0218348x25300119 · Cited by 1
Performance of Single-Layer Transformers in Stock-Price Trend Forecasting
Aşırım, Ö. E. (2025) · IEEE International Conference on Quantum Photonics, Artificial Intelligence & Networking (QPAIN) · doi:10.1109/qpain66474.2025.11171624 · Cited by 1
“The minimal impact of parameter sweeps on correlation performance also argues for focusing research efforts on richer input representations and multi-layer architectures if the goal is to improve point-wise accuracy [15,16].”
Financial Risk Control Model and Scenario Adaptation Method Based on Graph Machine Learning
Wang, M., & Quan, B. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-0985-0_22 · Cited by 1
Stock price prediction based on generative adversarial network
Lin, Y., Qin, Z., Song, B., & Tang, J. (2025) · Applied Economics · doi:10.1080/00036846.2025.2583485 · Cited by 1
LSTM-augmented DQN for quantitative trading in partially observable markets
Yu, H., Dong, J., Jiang, Y., & Sun, X. (2026) · Scientific Reports · doi:10.1038/s41598-026-49159-x · Cited by 2
“Early work, such as Moody & Saffell 28 , explored neural network-based RL trading frameworks, subsequently, Deng et al. 3 applied Deep Reinforcement Learning to stock trading, achieving end-to-end strategy learning.”
Reinforcement Learning in Portfolio Management: A Survey of Methods and Trends
Hu, S., Huang, Y., Agarwal, A., Warrier, T., Yuwen, W., Ma, H., & Luo, Z. (2025) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipaasc65261.2025.11249355 · Cited by 1
“Early research used algorithms like Q-learning [8], Recurrent RL [9], and deep direct reinforcement learning [10].”
Multi-Agent Reinforcement Learning for Secure and Adaptive Spectrum Allocation in 6G Networks
Mohammedali, N. A., Mohamed, A. N., Verma, P., & Mutalliyevich, D. A. (2025) · International Conference on Cyber Resilience (ICCR) · doi:10.1109/iccr67387.2025.11292370 · Cited by 1
“5 illustrates that the proposed MADQN system enables autonomous and scalable spectrum allocation in 6G networks through distributed multi-agent learning [2].”
Machine learning-based methods for frequency selective surfaces and metasurfaces
Rana, B., & Ic-Pyo, H. (2026) · Journal of Electromagnetic Waves and Applications · doi:10.1080/09205071.2025.2612299 · Cited by 2
“Machine learning techniques are being implemented in various areas like healthcare systems [30], autonomous driving [31], finance [32], credit card fraud detection [33], email spam and malware filtering [34], product recommendations [35], image recognition [36], etc. Typically, machine learning…”
Beyond random walks: exploring the learnability threshold of AI agents in algorithmic markets
Küçükoğlu, S. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.131776 · Cited by 2
Stock Market Analysis, Forecasting, and Automated Trading Using Deep Learning
Chang, C.-C., Wei, C.-H., Weng, J.-T., Cho, P.-H., & Hsiao, S. (2026) · IEEE International Conference on Computation, Big-Data and Engineering (ICCBE) · doi:10.3390/engproc2026128042 · Cited by 3
GenRL FinTech: supporting the risk management process through reinforcement intelligence
Sheikh, R., Miah, S. J., Skinner, J. L., III, & Cook, P. (2026) · Discover Artificial Intelligence · doi:10.1007/s44163-026-01133-2 · Cited by 1
Algorithmic trading by reinforcement learning in a collaborative manner
Li, L., Zhang, C., Ma, C., Wang, H., Ji, L., Gao, F., Zhang, J., & Qiu, K. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.115168 · Cited by 2
Rehman, M. S. U., & Gul, F. (2026) · Future Business Journal · doi:10.1186/s43093-026-00812-x · Cited by 2
A Fuzzy Risk Assessment Strategy Based on Big Data for Multinational Financial Markets
Su, C.-H., Lin, S.-C., Chang, C. J., & Huang, Y. (2018) · International Conference on System Science and Engineering · doi:10.1109/icsse.2018.8519983 · Cited by 1
Q-Learning-Based Financial Trading: Some Results and Comparisons
Corazza, M. (2020) · Smart innovation, systems and technologies · doi:10.1007/978-981-15-5093-5_31 · Cited by 1
Sato, Y., & Zhang, J. (2020) · International Conference on Awareness Science and Technology · doi:10.1109/icast51195.2020.9319476 · Cited by 1
“Although the models learn investment actions in previous research, Distributional Reinforcement Learning has not been applied to this field.”
MethodImage Representation of Time Series for Reinforcement Learning Trading Agent
da Costa, G. K., Coelho, L. D. S., & Freire, R. Z. (2020) · Congresso Brasileiro de Automática · doi:10.48011/asba.v2i1.1108 · Cited by 1
Technology Intelligence Map: Finance Machine Learning
Saadatmand, M., & Daim, T. U. (2021) · Applied innovation and technology management · doi:10.1007/978-3-030-50502-8_10 · Cited by 1
Mutual Deep Deterministic Policy Gradient Learning
Sun, Z. (2022) · International Conference on Big Data, Information and Computer Network (BDICN) · doi:10.1109/bdicn55575.2022.00099 · Cited by 1
Evolutionary DRL Environment: Transfer Learning-Based Genetic Algorithm
Hirchoua, B., Mountasser, I., Ouhbi, B., & Frikh, B. (2022) · Journal of Data Intelligence · doi:10.26421/jdi3.3-3 · Cited by 1
Researches advanced in financial trading systems based on reinforcement learning
Zhu, H. (2022) · International Conference on Artificial Intelligence, Automation and High Performance Computing (AIAHPC) · doi:10.1117/12.2641867 · Cited by 2
“Combined with other algorithms, actor-critic algorithms are more widely used in financial trading systems [9].”
MethodScalp the Foreign Exchange Market with Deep Reinforcement Learning
Tropmann-Frick, M., & Tran, P. (2023) · Frontiers in artificial intelligence and applications · doi:10.3233/faia220494 · Cited by 1
A hybrid multicategory framework for generating automated trading systems
Kumar, D., Sahoo, K., & Thakur, M. (2023) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.7746 · Cited by 1
“The decision boundary for the ith class is identified by using the optimal value of the parameters found in equation (13).”
MethodGeneralized Deep Reinforcement Learning for Trading
Sim, J., & Kirk, B. (2023) · Journal of Student Research · doi:10.47611/jsrhs.v12i1.4316 · Cited by 3
Hybrid Heterogeneous Graph Neural Networks for Fund Performance Prediction
Hao, S., Dai, L., Zhang, L., Zhang, S., Wang, C., Qin, C., & Xiong, H. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-40286-9_25 · Cited by 1
Mtetwa, J. T., Ogudo, K. A., & Pudaruth, S. (2023) · International Conference on Artificial Intelligence, Big Data, Computing and Data Communication Systems (icABCD) · doi:10.1109/icabcd59051.2023.10220544 · Cited by 1
An LSTM-Driven Decision-Support Framework for Small and Medium-Sized Investors
Chen, Y., Li, R., He, W., & Ni, Z. (2023) · IEEE International Conference on Software Engineering and Service Science (ICSESS) · doi:10.1109/icsess58500.2023.10293115 · Cited by 1
“Renowned for its prowess in processing financial time series data [10], LSTM has garnered attention in several studies vouching for its efficacy in predicting financial market trends [11][12].”
BackgroundApplication of machine learning in quantitative timing model based on factor stock selection
Duan, Y., Gu, X., & Lei, T. (2023) · Electronic Research Archive · doi:10.3934/era.2024009 · Cited by 2
“To improve the generalization ability and meet the demands of dynamic behavior of trading action execution, Deng et al. [13] introduced the contemporary deep learning into a typical direct reinforcement learning framework, but such a research only handled one share of the asset.”
BackgroundMethodFinancial Zen: Achieving Market Harmony through Reinforcement Learning and Algorithmic Trading
Sowmya, M. R., Chhetri, D. K., Chai, K., Rohit, & Ashraf, S. (2024) · International Conference on Data Science and Information System (ICDSIS) · doi:10.1109/icdsis61070.2024.10594381 · Cited by 1
“Studies such as those by Tang and Jagwani et al. have investigated stock price forecasting using different methodologies [10], [11], while Bangroo et al. explored machine learning algorithms for cryptocurrency price prediction [12].”
MethodHIT: Solving Partial Index Tracking via Hierarchical Reinforcement Learning
Zheng, Z., Shao, J., Chen, F., Zhu, A., Deng, S., & Shen, H. T. (2024) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde60146.2024.00358 · Cited by 2
“…of selected assets does not exceed the predefined value K . c) Reward : Different from previous reinforcement learning based trading tasks [27], [28], [37] that aim to maximize investment profit, the primary objective of PIT is to closely replicate a chosen index while controlling transaction cost.”
BackgroundEnhancing Market Making Strategies with Deep Reinforcement Learning-Based Quoting Decisions
Ekarittikrai, C., & Rattagan, E. (2024) · International Joint Conference on Computer Science and Software Engineering · doi:10.1109/jcsse61278.2024.10613677
“Among the most promising approaches to tackle this challenge is deep reinforcement learning (DRL) [6]–[8], [16].”
Background
Metadata
- Authors
- Deng, Y., Bao, F., Kong, Y., Ren, Z., & Dai, Q.
- Affiliations
- University of California, San Francisco (US)
- Tsinghua University (CN)
- Southeast University (CN)
- Venue
- IEEE Transactions on Neural Networks and Learning Systems
- Published
- 2017-03
- Volume
- 28
- Issue
- 3
- Pages
- 653-664
- ISSN
- 2162-237X (ISSN-L)
- 2162-2388
- OpenAlex
- W2344786740
- Cited by
- 822
- References
- 51
- Citations by year
- 2026: 90 · 2025: 90 · 2024: 95 · 2023: 110 · 2022: 109 · 2021: 100 · 2020: 98 · 2019: 76 · 2018: 40 · 2017: 10
- FWCI
- 47.14
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Transactions on Neural Networks and Learning Systems (publishedVersion)
- PubMed (publishedVersion)
- Funders
- Project of the National Natural Science Foundation of China (61327902, 61120106003)
- National Science Foundation of Jiangsu Province, China (BK20150650)
- Topics
- Social Sciences › Decision Sciences › Management Science and Operations Research › Stock Market Forecasting Methods
- Social Sciences › Economics, Econometrics and Finance › Finance › Financial Markets and Investment Strategies
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- Keywords
- deep reinforcement learning, financial trading, recurrent neural networks, backpropagation through time, gradient vanishing, stock market, commodity futures, trading decision-making, representation learning
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.