LLM-based Personalized Portfolio Recommender: Integrating Large Language Models and Reinforcement Learning for Intelligent Investment Strategy Optimization
DOI:
https://doi.org/10.66238/fsrma83Keywords:
Large Language Models (LLM), Reinforcement Learning, Personalized Portfolio Optimization, Risk Preference Modeling, Financial Recommendation Systems, Proximal Policy Optimization (PPO)Abstract
In modern financial markets, investors increasingly seek personalized and adaptive portfolio strategies that reflect their individual risk preferences and respond to dynamic market conditions. Traditional rule-based or static optimization approaches often fail to capture the nonlinear interactions among investor behavior, market volatility, and evolving financial objectives. To address these limitations, this paper introduces the LLM-based Personalized Portfolio Recommender (L-PPR), an integrated framework that combines Large Language Models (LLMs), reinforcement learning, and individualized risk preference modeling to support intelligent investment decision-making. The proposed system comprises three core components: (1) a Conversational Financial Agent (FinAgent) that engages with users through natural language, gathers behavioral feedback, and delivers interpretable advisory explanations; (2) a Personalization and Risk Modeling Module that infers investor-specific risk tolerance using Bayesian inference and behavioral imitation learning; and (3) a Strategy Recommendation Engine based on Proximal Policy Optimization (PPO) that generates personalized asset allocation strategies conditioned on user embeddings and real-time market states. Experimental results on a simulated multi-asset portfolio dataset show that L-PPR substantially outperforms established baselines, including Mean–Variance Optimization (MVO), Deep Reinforcement Learning Portfolio (DRL-PPO), and BERT-based Financial Advisor (BERT-FA). Specifically, L-PPR achieves a 73.8% improvement in annualized return and a 33.2% reduction in maximum drawdown relative to MVO. It also records the highest Sharpe Ratio (1.45), Information Ratio (0.78), and User Alignment Score (0.89). These findings demonstrate that L-PPR effectively enhances risk-adjusted performance while delivering superior personalization and user satisfaction.
References
[1] Majka M. Capital Asset Pricing Model (CAPM)[J].
[2] Jiang Z, Xu D, Liang J. A deep reinforcement learning framework for the financial portfolio management problem[J]. arXiv preprint arXiv:1706.10059, 2017.
[3] Moody J, Saffell M. Learning to trade via direct reinforcement[J]. IEEE transactions on neural Networks, 2001, 12(4): 875-889.
[4] Wang X, Liu L. Risk-Sensitive Deep Reinforcement Learning for Portfolio Optimization[J]. Journal of Risk and Financial Management, 2025, 18(7): 347.
[5] Nigatu B. A Multi-Objective, Multiperiod Portfolio Optimization Using Particle Swarm Optimization and Asynchronous Advantage Actor-Critic: Investors’ Behavioral Characterization[D]. Colorado Technical University, 2020.
[6] Xu S, Jiang L, Gu B. Design and Validation of a Smart Neuromorphic System Architecture for Algorithmic Trading[C]//Proceedings of the 2nd International Symposium on Integrated Circuit Design and Integrated Systems. 2025: 127-136.
[7] Luo R, Hu J, Sun Q. Group Anomaly Detection and Risk Control of Commodity Sales Volume Data Based on LSTM-VAE Framework[J]. Journal of Computer, Signal, and System Research, 2025, 2(7): 48-57.
[8] Loughran T, McDonald B. When is a liability not a liability? Textual analysis, dictionaries, and 10‐Ks[J]. The Journal of finance, 2011, 66(1): 35-65.
[9] Devlin J, Chang M W, Lee K, et al. Bert: Pre-training of deep bidirectional transformers for language understanding[C]//Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers). 2019: 4171-4186.
[10] Araci D. Finbert: Financial sentiment analysis with pre-trained language models[J]. arXiv preprint arXiv:1908.10063, 2019.
[11] Sever Y S, Artan B N, Danışman B, et al. FinSentio: A Modular LLM-Powered Financial Assistant for Investment Guidance, Risk Analysis, and Education[C]//2025 10th International Conference on Computer Science and Engineering (UBMK). IEEE, 2025: 119-124.
[12] Xiao M, Jiang Z, Qian L, et al. Retrieval-augmented large language models for financial time series forecasting[J]. arXiv preprint arXiv:2502.05878, 2025.
[13] Ricc F, Rokach L, Shapira B. Recommender Systems Handbook[J]. NY: Springer, 2011: 1-35.
[14] Yu J R, Chiou W P, Hung C H, et al. Dynamic rebalancing portfolio models with analyses of investor sentiment[J]. International Review of Economics & Finance, 2022, 77: 1-13.
[15] Zhang G, Zeng H, Jiang L. Uni-FinLLM: A Unified Multimodal Large Language Model with Modular Task Heads for Micro-Level Stock Prediction and Macro-Level Systemic Risk Assessment[J]. arXiv preprint arXiv:2601.02677, 2026.
[16] Li B, Gu B, Ding Z. LLM-based Personalized Portfolio Recommender: Integrating Large Language Models and Reinforcement Learning for Intelligent Investment Strategy Optimization[J]. arXiv preprint arXiv:2512.12922, 2025.
Toor, M. J., Shabbir, S., Rauf, A., Nisar, A., Safdar, S., & Zaib-Un-Nisa. (n.d.). The role of structured-communication-technique in developing pragmatic language capability among ASD-children. https://doi.org/10.63878/cjssr.v3i2.785
Toor, M. J., Mehmood, H., Yasmeen, A., Honey, Q., Waseem, M., & Wasif, M. (n.d.). Exploring the effect of verbal encouraging phrases (VEP) on Chinese language learners’ academic achievement at university level.
Toor, M. J., Arafat, M., Ayoub, M., Ali, M., & Alessi Longa, F. E. (n.d.). From coherent self to fragmented persona: Digital identity fragmentation and academic self-concept among Generation Z, with comparative insights from Generation Alpha. https://doi.org/10.63878/cjssr.v4i2.2318
Katsitadze, N., Kharadze, N., & Pirtskhalaishvili, D. (2025). The impact of social media on students’ effective time management. Baltic Journal of Economic Studies, 11(1), 200–210. https://doi.org/10.30525/2256-0742/2025-11-1-200-210
Toor, M. J., Zafar, S., Omer, F., Sarwar, M., & Hussain, A. K. (n.d.). Teachers’ perspectives on effectiveness of translanguaging in enhancing English language learning at secondary school level.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Bangyu Li, Boping Gu, Ziyang Ding
This work is licensed under a Creative Commons Attribution 4.0 International License.
License Terms (Recommended – CC BY 4.0)
All articles published in Fundamental Scientific Reports in Multidisciplinary Areas are licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0).
This license permits unrestricted use, distribution, and reproduction in any medium, provided the original author(s) and source are properly cited. Users are allowed to copy, redistribute, remix, transform, and build upon the material for any purpose, including commercial use, as long as appropriate credit is given.
Authors retain copyright of their work while granting the journal the right of first publication. The journal provides immediate open access to its content on the principle that making research freely available supports a greater global exchange of knowledge.
For more information about this license, visit:
https://creativecommons.org/licenses/by/4.0/
