{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T07:06:55Z","timestamp":1773817615877,"version":"3.50.1"},"reference-count":33,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T00:00:00Z","timestamp":1773619200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012456","name":"National Social Science Foundation of China","doi-asserted-by":"publisher","award":["23BTJ054"],"award-info":[{"award-number":["23BTJ054"]}],"id":[{"id":"10.13039\/501100012456","id-type":"DOI","asserted-by":"publisher"}]},{"name":"open project of Joint Lab for Statistics and Finance of Nanjing Audit University","award":["2025JLSF309"],"award-info":[{"award-number":["2025JLSF309"]}]},{"name":"open project of Joint Lab for Statistics and Finance of Nanjing Audit University","award":["2025JLSF315"],"award-info":[{"award-number":["2025JLSF315"]}]},{"name":"open project of Joint Lab for Statistics and Finance of Nanjing Audit University","award":["2025JLSF323"],"award-info":[{"award-number":["2025JLSF323"]}]},{"DOI":"10.13039\/501100000038","name":"Natural Science and Engineering Research Council of Canada","doi-asserted-by":"crossref","award":["RGPIN-2023-05655"],"award-info":[{"award-number":["RGPIN-2023-05655"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Axioms"],"abstract":"<jats:p>Financial data analysis remains a significant challenge due to the inherent stochasticity, non-stationarity, and low signal-to-noise ratio of market data. Conventional methods often struggle to disentangle intrinsic trends from noise and frequently overlook the critical influence of investor sentiment on price dynamics. To address these issues, we propose an adaptive trading model named CBAM-BiLSTM-DDQN, which integrates signal decomposition, multi-source feature fusion, and deep reinforcement learning. First, we construct a comprehensive heterogeneous feature set by combining price signals decomposed via Variational Mode Decomposition (VMD) and investor sentiment indices extracted from financial texts. Subsequently, a Genetic Algorithm (GA) is employed to identify the most significant feature subset, effectively reducing dimensionality and redundancy. Finally, these optimized features are input into a Double Deep Q-Network (DDQN) agent equipped with a Convolutional Block Attention Module (CBAM) and a Bidirectional Long Short-Term Memory (BiLSTM) network to capture complex spatiotemporal dependencies. We evaluated this approach through simulated trading on three major Chinese stock indices\u2014the Shanghai Stock Exchange Composite (SSEC), the Shenzhen Stock Exchange Component (SZSE), and the China Securities 300 (CSI 300). Experimental results demonstrate the superiority of our method over traditional strategies and standard baselines; specifically, the trading agent achieved robust cumulative returns across the SSEC and CSI 300 indices, confirming the model\u2019s exceptional capability in balancing profitability and risk aversion in complex financial environments. Furthermore, additional experiments on individual stocks in the Chinese A-share market reinforce the robustness and generalization ability of our proposed model, validating its practical potential for diverse trading scenarios. Furthermore, additional experiments on individual stocks in the Chinese A-share market reinforce the robustness and generalization ability of our proposed model, validating its practical potential for diverse trading scenarios.<\/jats:p>","DOI":"10.3390\/axioms15030222","type":"journal-article","created":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T13:32:07Z","timestamp":1773667927000},"page":"222","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CBAM-BiLSTM-DDQN: A Novel Adaptive Quantitative Trading Model for Financial Data Analysis"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-2431-5749","authenticated-orcid":false,"given":"Yan","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Statistics and Data Science and Joint Lab for Statistics and Finance, Nanjing Audit University, Nanjing 211815, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingxuan","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Statistics and Data Science and Joint Lab for Statistics and Finance, Nanjing Audit University, Nanjing 211815, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Statistics and Data Science and Joint Lab for Statistics and Finance, Nanjing Audit University, Nanjing 211815, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8858-1289","authenticated-orcid":false,"given":"Yuehua","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Statistics, York University, Toronto, ON M3J 1P3, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,3,16]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1287\/moor.1.2.97","article-title":"Augmented Lagrangians and applications of the proximal point algorithm in convex programming","volume":"1","author":"Rockafellar","year":"1976","journal-title":"Math. Oper. Res."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/2200000016","article-title":"Distributed optimization and statistical learning via the alternating direction method of multipliers","volume":"3","author":"Boyd","year":"2011","journal-title":"Found. Trends Mach. Learn."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"903","DOI":"10.1098\/rspa.1998.0193","article-title":"The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis","volume":"454","author":"Huang","year":"1998","journal-title":"Proc. R. Soc. Lond. A"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"531","DOI":"10.1109\/TSP.2013.2288675","article-title":"Variational mode decomposition","volume":"62","author":"Dragomiretskiy","year":"2014","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Zhou, J., and Wang, S. (2021). A carbon price prediction model based on the secondary decomposition algorithm and influencing factors. Energies, 14.","DOI":"10.3390\/en14051328"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Pu, H., Wu, Y., Hua, C., Song, Z., Zhang, W., Zhang, L., Chu, Q., and Qiu, Y. (2022, January 19\u201321). Carbon trading based on quadratic modal decomposition and recurrent neural network price prediction model. Proceedings of the 2022 5th International Conference on Pattern Recognition and Artificial Intelligence (PRAI), Chengdu, China.","DOI":"10.1109\/PRAI55851.2022.9904232"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"2450002.","DOI":"10.1142\/S2424786324500026","article-title":"Carbon trading price forecasting based on parameter optimization VMD and deep network CNN\u2013LSTM model","volume":"11","author":"Ling","year":"2024","journal-title":"Int. J. Financ. Eng."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"140322","DOI":"10.1016\/j.jclepro.2023.140322","article-title":"Research on carbon asset trading strategy based on PSO-VMD and deep reinforcement learning","volume":"435","author":"Zhang","year":"2024","journal-title":"J. Clean. Prod."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Cover, T.M., and Thomas, J.A. (2006). Elements of Information Theory, Wiley. [2nd ed.].","DOI":"10.1002\/047174882X"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Vershynin, R. (2018). High-Dimensional Probability: An Introduction with Applications in Data Science, Cambridge University Press.","DOI":"10.1017\/9781108231596"},{"key":"ref_11","first-page":"5497","article-title":"SABER: A multimodal sentiment aware regression framework using ROBERTa BiLSTM and deep batch active learning for stock market prediction","volume":"17","author":"Singh","year":"2025","journal-title":"Int. J. Inf. Technol."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Poornima, N., Abilash, D., and Theodaniel, M. (2023, January 25\u201326). Improvising the stock prediction by integrating with roBERTa and LSTM. Proceedings of the 2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT), Karaikal, India.","DOI":"10.1109\/IConSCEPT57958.2023.10169904"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"21517","DOI":"10.1109\/ACCESS.2022.3152828","article-title":"RoBERTa-LSTM: A hybrid model for sentiment analysis with transformer and recurrent neural network","volume":"10","author":"Tan","year":"2022","journal-title":"IEEE Access"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Tan, K., Lee, C., and Lim, K. (2023). Roberta-gru: A hybrid deep learning model for enhanced sentiment analysis. Appl. Sci., 13.","DOI":"10.3390\/app13063915"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Pradeep, P., Premjith, B., Nimal Madhu, M., and Gopalakrishnan, E.A. (2024, January 8\u201310). A transformer-based stock market price prediction by incorporating BERT embedding. Proceedings of the International Conference on Mathematics and Computing, Nanjing, China.","DOI":"10.1007\/978-981-97-2066-8_10"},{"key":"ref_16","first-page":"1018","article-title":"Stock price prediction based on investor sentiment using BERT and transformer models","volume":"11","author":"Lee","year":"2023","journal-title":"Stat. Optim. Inf. Comput."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Friday, I.K., Mishra, S., Pati, S.P., and Mishra, D. (2025, January 27\u201328). A transformer-based stock trend prediction with sentiment analysis of relevant and urgent tweets. Proceedings of the 2025 International Conference on Innovations in Intelligent Systems: Advancements in Computing, Communication, and Cybersecurity (ISAC3), Silchar, India.","DOI":"10.1109\/ISAC364032.2025.11156488"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Putri, R.A., and Oktavia, T. (2025, January 10\u201312). Analyzing Twitter Sentiment on Stock Using the Bidirectional Encoder Representations (BERT) Based on the Transformer Model. Proceedings of the 2025 29th International Conference on Information Technology (IT), Hong Kong, China.","DOI":"10.1109\/IT64745.2025.10930290"},{"key":"ref_19","unstructured":"Yu, Y. (2025). Multi-Factor Prediction of Stock Market Index Based on LSTM Neural Networks with BERT Embedding. [Master\u2019s Thesis, Univerzita Karlova]."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"248.","DOI":"10.1007\/s10791-025-09515-3","article-title":"Integrating Taiwan financial BERT sentiment analysis with CNN-BiLSTM-SA model for stock prediction","volume":"28","author":"Chen","year":"2025","journal-title":"Discov. Comput."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Sakilam, A., Rangarajan, P.K., Bode, V., and Nalla, B.T. (2024, January 15\u201317). Deep Reinforcement Learning Algorithms for Profitable Stock Trading Strategies. Proceedings of the 2024 IEEE International Conference on Contemporary Computing and Communications (InC4), Bangalore, India.","DOI":"10.1109\/InC460750.2024.10649326"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Tran, M., Pham-Hi, D., and Bui, M. (2023). Optimizing automated trading systems with deep reinforcement learning. Algorithms, 16.","DOI":"10.3390\/a16010023"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Huang, Y., Lu, X., Zhou, C., and Zhang, L. (2023). DADE-DQN: Dual action and dual environment deep q-network for enhancing stock trading strategy. Mathematics, 11.","DOI":"10.3390\/math11173626"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Huang, Y., Zhou, C., Zhang, L., and Lu, X. (2024). A Self-Rewarding Mechanism in Deep Reinforcement Learning for Trading Strategy Optimization. Mathematics, 12.","DOI":"10.3390\/math12244020"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"32308","DOI":"10.1109\/ACCESS.2023.3259424","article-title":"A novel convolutional neural networks for stock trading based on DDQN algorithm","volume":"11","author":"Cui","year":"2023","journal-title":"IEEE Access"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"290","DOI":"10.1016\/j.neucom.2021.04.005","article-title":"A parallel multi-module deep reinforcement learning algorithm for stock trading","volume":"449","author":"Ma","year":"2021","journal-title":"Neurocomputing"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Chen, X., Wang, Q., Hu, C., and Zhu, Y. (2024). A stock market decision-making framework based on CMR-DQN. Appl. Sci., 14.","DOI":"10.3390\/app14166881"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Engl, H.W., Hanke, M., and Neubauer, A. (1996). Regularization of Inverse Problems, Springer.","DOI":"10.1007\/978-94-009-1740-8"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.-Y., and Kweon, I.S. (2018, January 8\u201314). CBAM: Convolutional block attention module. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"ref_30","unstructured":"Graves, A., and Schmidhuber, J. (August, January 31). Framewise phoneme classification with bidirectional LSTM networks. Proceedings of the IEEE International Joint Conference on Neural Networks, Montreal, QC, Canada."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Cui, Y., Che, W., Liu, T., Qin, B., Wang, S., and Hu, G. (2020). Revisiting pre-trained models for Chinese natural language processing. arXiv.","DOI":"10.18653\/v1\/2020.findings-emnlp.58"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Van Hasselt, H., Guez, A., and Silver, D. (2016, January 12\u201317). Deep reinforcement learning with double q-learning. Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, Phoenix, AZ, USA.","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"115019","DOI":"10.1016\/j.eswa.2021.115019","article-title":"A hybrid model integrating deep learning with investor sentiment analysis for stock price prediction","volume":"178","author":"Jing","year":"2021","journal-title":"Expert Syst. Appl."}],"container-title":["Axioms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-1680\/15\/3\/222\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T06:07:33Z","timestamp":1773814053000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-1680\/15\/3\/222"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,16]]},"references-count":33,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3]]}},"alternative-id":["axioms15030222"],"URL":"https:\/\/doi.org\/10.3390\/axioms15030222","relation":{},"ISSN":["2075-1680"],"issn-type":[{"value":"2075-1680","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,16]]}}}