{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T04:38:35Z","timestamp":1773203915704,"version":"3.50.1"},"reference-count":33,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T00:00:00Z","timestamp":1709164800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Ministry of Education","award":["2021R1F1A1050120"],"award-info":[{"award-number":["2021R1F1A1050120"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>The objective of portfolio diversification is to reduce risk and potentially enhance returns by spreading investments across different asset classes. Existing portfolio diversification models have traditionally been trained on historical financial time series data. However, several issues arise with historical financial time series data, making it challenging to train models effectively to achieve the portfolio diversification objective: an insufficient amount of training data and the uncertainty deficiency problem, wherein the uncertainty that existed in the past is not visible in the present. Insufficient datasets, characterized by small data size, result in information asymmetry and compromise portfolio performance. This limitation underscores the importance of adopting a pattern-centric data augmentation approach, capable of unveiling hidden patterns and structures within the financial time series data. To address these challenges, this paper introduces the financial time series decomposition-based variational encoder-decoder (FED) method to augment financial time series data, overcoming the limitations of insufficient training data and providing a more realistic and dynamic simulation of the financial market environment. By decomposing the data into distinct components, such as trend, dispersion, and residual, FED leverages pattern-centric data augmentation within the financial time series data. In the environment generated using the FED method, this paper proposes a two-class portfolio diversification, called FED2Port. It integrates stochastic elements into the reward function, enabling a reinforcement learning algorithm to learn from a comprehensive spectrum of financial market uncertainties. The experimental results demonstrate that the proposed model significantly enhances portfolio performance.<\/jats:p>","DOI":"10.3390\/sym16030283","type":"journal-article","created":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T06:07:53Z","timestamp":1709273273000},"page":"283","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Enhancing Portfolio Performance through Financial Time-Series Decomposition-Based Variational Encoder-Decoder Data Augmentation"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4929-3145","authenticated-orcid":false,"given":"Bayartsetseg","family":"Kalina","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Inha University, Incheon 22212, Republic of Korea"}]},{"given":"Ju-Hong","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Inha University, Incheon 22212, Republic of Korea"}]},{"given":"Kwang-Tek","family":"Na","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Inha University, Incheon 22212, Republic of Korea"}]}],"member":"1968","published-online":{"date-parts":[[2024,2,29]]},"reference":[{"key":"ref_1","unstructured":"(2024, January 22). Pensions at a Glance 2021: OECD and G20 Indicators. Available online: https:\/\/www.oecd-ilibrary.org\/finance-and-investment\/pensions-at-a-glance-2021_ca401ebd-en."},{"key":"ref_2","unstructured":"(2024, January 22). Asset Allocation of Pension Funds. Available online: https:\/\/www.monash.edu\/__data\/assets\/pdf_file\/0003\/2357238\/Research-1-Asset-allocation-of-pension-funds.pdf."},{"key":"ref_3","first-page":"77","article-title":"Portfolio Selection","volume":"7","author":"Markowitz","year":"1952","journal-title":"J. Financ."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Roncalli, T. (2014). Introduction to Risk Parity and Budgeting. arXiv.","DOI":"10.2139\/ssrn.2272973"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Richard, J.E., and Roncalli, T. (2019). Constrained Risk Budgeting Portfolios: Theory, Algorithms, Applications & Puzzles. arXiv.","DOI":"10.2139\/ssrn.3331184"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1002\/(SICI)1099-131X(1998090)17:5\/6<441::AID-FOR707>3.0.CO;2-#","article-title":"Performance Functions and Reinforcement Learning for Trading Systems and Portfolios","volume":"17","author":"Moody","year":"1998","journal-title":"J. Forecast."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Li, L. (2021). Financial Trading with Feature Preprocessing and Recurrent Reinforcement Learning. arXiv.","DOI":"10.1145\/3490354.3494376"},{"key":"ref_8","unstructured":"Liu, X., Xiong, Z., Zhong, S., Yang, H., and Walid, A. (2018). Practical Deep Reinforcement Learning Approach for Stock Trading. arXiv."},{"key":"ref_9","unstructured":"Kalina, B., Lee, J., and Song, J. (2020, January 29\u201330). A Study on Portfolio Asset Allocation Using Actor-Critic Model. Proceedings of the Korea Information Processing Society Conference, Online."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1016\/j.eswa.2017.06.023","article-title":"An adaptive portfolio trading system: A risk-return portfolio optimization using recurrent reinforcement learning with expected maximum drawdown","volume":"87","author":"Almahdi","year":"2017","journal-title":"Expert Syst. Appl."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.eswa.2018.02.032","article-title":"Trading financial indices with reinforcement learning agents","volume":"102","author":"Pendharker","year":"2018","journal-title":"Expert Syst. Appl."},{"key":"ref_12","unstructured":"Mirza, M., and Osindero, S. (2014). Conditional Generative Adversarial Nets. arXiv."},{"key":"ref_13","unstructured":"Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014, January 8\u201313). Generative Adversarial Nets. Proceedings of the 27th Conference on Neural Information Processing Systems, Montr\u00e9al, QC, Canada."},{"key":"ref_14","unstructured":"Kingma, D.P., and Welling, M. (2013). Auto-Encoding Variational Bayes. arXiv."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Kingma, D.P., and Welling, M. (2019). An Introduction to Variational Autoencoders. arXiv.","DOI":"10.1561\/9781680836233"},{"key":"ref_16","unstructured":"Yoon, J., Jarrett, D., and Schaar, M.v. (2019, January 8\u201314). Time-series Generative Adversarial Networks. Proceedings of the 33rd Conference on Neural Information Processing Systems, Vancouver, BC, Canada."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Pei, H., Ren, K., Yang, Y., Liu, C., Qin, T., and Li, D. (2021, January 7\u201310). Towards Generating Real-World Time Series Data. Proceedings of the 2021 IEEE International Conference on Data Mining (ICDM), Auckland, New Zealand.","DOI":"10.1109\/ICDM51629.2021.00058"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"489","DOI":"10.1093\/biomet\/84.2.489","article-title":"Time Series Decomposition","volume":"84","author":"West","year":"1997","journal-title":"Biometrika"},{"key":"ref_19","unstructured":"Wen, Q., Gao, J., Song, X., Sun, L., Xu, H., and Zhu, S. (February, January 27). RobustSTL: A Robust Seasonal-Trend Decomposition Algorithm for Long Time Series. Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence, Honolulu, HI, USA."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Patidar, S., Jenkins, D.P., Peacock, A., and McCallum, P. (2019, January 2\u20134). Time Series Decomposition Approach for Simulating Electricity Demand Profile. Proceedings of the 16th IBPSA Conference, Rome, Italy.","DOI":"10.26868\/25222708.2019.210541"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Wen, Q., Zhang, Z., Li, Y., and Sun, L. (2020, January 6\u201310). Fast RobustSTL: Efficient and Robust Seasonal-Trend Decomposition for Time Series with Complex Patterns. Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Online.","DOI":"10.1145\/3394486.3403271"},{"key":"ref_22","unstructured":"Hyndman, R.J., and Athanasopoulos, G. (2021). Forecasting: Principles and Practice, OTexts. [3rd ed.]. Chapter 3."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1287\/ijds.2021.0004","article-title":"STR: Seasonal-Trend Decomposition Using Regression","volume":"1","author":"Dokumentov","year":"2021","journal-title":"INFORMS J. Data Sci."},{"key":"ref_24","unstructured":"Mishra, A., Sriharsha, R., and Zhong, S. (2021). OnlineSTL: Scaling Time Series Decomposition by 100x. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Jiang, S., Syed, T., Zhu, X., Levy, J., and Aronchik, B. (2022, January 17\u201321). Bridging Self-Attention and Time Series Decomposition for Periodic Forecasting. Proceedings of the 31st ACM International Conference on Information & Knowledge Management, Atlanta, GA, USA.","DOI":"10.1145\/3511808.3557077"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"10339","DOI":"10.1109\/TKDE.2023.3268125","article-title":"STD: A Seasonal-Trend-Dispersion Decomposition of Time Series","volume":"35","author":"Dudek","year":"2023","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1086\/294846","article-title":"Mutual Fund Performance","volume":"39","author":"Sharpe","year":"1966","journal-title":"J. Bus."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"28","DOI":"10.2469\/faj.v48.n5.28","article-title":"Global Portfolio Optimization","volume":"48","author":"Black","year":"1992","journal-title":"Financ. Anal. J."},{"key":"ref_29","first-page":"425","article-title":"Capital asset prices: A theory of market equilibrium under conditions of risk","volume":"19","author":"Sharpe","year":"1964","journal-title":"J. Financ."},{"key":"ref_30","unstructured":"Lillicrap, T.P., Hunt, J.J., Pritzel, A., Heess, N., Erez, T., Tassa, Y., Silver, D., and Wierstra, D. (2015). Continuous control with deep reinforcement learning. arXiv."},{"key":"ref_31","first-page":"59","article-title":"Performance measurement in a downside risk framework","volume":"3","author":"Sortino","year":"1994","journal-title":"J. Investig."},{"key":"ref_32","unstructured":"Lee, J.H., Kalina, B., and Na, K. (2023). Market-Adaptive Ratio for Portfolio Management. arXiv."},{"key":"ref_33","unstructured":"Peterson, K.B., and Pedersen, M.S. (2012). The Matrix Cookbook, Technical University of Denmark."}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/16\/3\/283\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T14:07:26Z","timestamp":1760105246000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/16\/3\/283"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,29]]},"references-count":33,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2024,3]]}},"alternative-id":["sym16030283"],"URL":"https:\/\/doi.org\/10.3390\/sym16030283","relation":{},"ISSN":["2073-8994"],"issn-type":[{"value":"2073-8994","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,29]]}}}