Can AI Agent Be the New Assistant to Robo-Advisers?

Yong HE, Yi YANG, Yan CHEN, Mingzhu HU

China Journal of Econometrics ›› 2025, Vol. 5 ›› Issue (3) : 818-841.

PDF(1542 KB)
PDF(1542 KB)
China Journal of Econometrics ›› 2025, Vol. 5 ›› Issue (3) : 818-841. DOI: 10.12012/CJoE2024-0422

Can AI Agent Be the New Assistant to Robo-Advisers?

  • Yong HE1,2,*(Email), Yi YANG1(Email), Yan CHEN1(Email), Mingzhu HU1(Email)
Author information +
History +

Abstract

The rise of large language models has injected fresh vigor into the development of Robo-advisors in China and promoted the innovation of financial technology. In this context, this paper constructs an AI agent based on the domestic generative language model framework, from sentiment analysis, market prediction, factor indicators and other dimensions, in-depth mining of alternative data and traditional financial data in stock trading signals, and then constructs the Chinese stock market investment and trading strategies. Empirical studies show that AI agent based on the domestic large models have the potential to perform quantitative analysis, and that the investment returns under the combined multiple dimensions will be significantly better than the results of a single dimension. This suggests that by utilizing powerful natural language processing capabilities and data analysis capabilities, the application of domestic large models in Robo-advisors is promising, providing new ideas and methods for the continuous development of quantitative investment. With the evolution of technology, the future AI agent will be able to understand market dynamics and investor needs more deeply, thus providing more targeted support for investment decisions, enhancing overall investment returns and creating more value.

Key words

AI agent / large language models / Robo-advisors / multimodal data

Cite this article

Download Citations
Yong HE, Yi YANG, Yan CHEN, Mingzhu HU. Can AI Agent Be the New Assistant to Robo-Advisers?. China Journal of Econometrics, 2025, 5(3): 818-841 https://doi.org/10.12012/CJoE2024-0422

References

陈张杭健, 吴粤, 李世炳, 任飞, (2021). 股吧个体信息交互对股价联动关系的影响研究[J]. 管理科学学报, 24(5): 47-69.
Chen Z H J, Wu Y, Li S B, Ren F, (2021). The Impact of Individuals' Information Interaction in Stock Bars on Stock Price Co-movement[J]. Journal of Management Sciences in China, 24(5): 47-69.
方思然, 郭明君, 魏云捷, (2023). 加入舆情信息是否可以有效提高汇率预测效果?[J]. 计量经济学报, 3(2): 464-486.
Fang S R, Guo M J, Wei Y J, (2023). Is the Inclusion of Public Opinion Information Effective in Improving Exchange Rate Forecasting?[J]. China Journal of Econometrics, 3(2): 464-486.
何勇, 李琪琪, 焦丽, 黄文萱, (2023). 另类数据在中国股票市场投资中有用吗?——基于财经短视频、图像、文本数据的探究[J]. 计量经济学报, 3(4): 1008-1031.
He Y, Lee Q Q, Jiao L, Huang W X, (2023). Is Alternative Data Useful in Chinese Stock Market Investment?—An Exploration Based on Financial Short Videos, Images, and Text Data[J]. China Journal of Econometrics, 3(4): 1008-1031.
何勇, 焦丽, 杨艺, 祝怡菲, (2024). AI 大模型赋能金融市场量化投资? 基于另类数据与传统金融数据的研究[J]. 计量经济学报, 4(3): 761-783.
He Y, Jiao L, Yang Y, Zhu Y F, (2024). AI Large Language Model Empowers Quantitative Investment in Financial Markets? Research Based on Alternative Data and Traditional Financial Data[J]. China Journal of Econometrics, 4(3): 761-783.
洪永淼, 汪寿阳, (2021). 大数据如何改变经济学研究范式?[J]. 管理世界, 37(10): 40-55.
Hong Y M, Wang S Y, (2021). How is Big Data Changing Economic Research Paradigms?[J]. Management World, 37(10): 40-55.
洪永淼, 汪寿阳, (2024). ChatGPT与大模型将对经济学研究范式产生什么影响?[J]. 计量经济学报, 4(1): 1-25.
Hong Y M, Wang S Y, (2024). How Will ChatGPT and Large Models Influence the Research Paradigm in Economics?[J]. China Journal of Econometrics, 4(1): 1-25.
胡楠, 薛付婧, 王昊楠, (2021). 管理者短视主义影响企业长期投资吗?——基于文本分析和机器学习[J]. 管理世界, 37(5): 139-156.
Hu N, Xue F J, Wang H N, (2021). Does Managerial Myopia Affect Long-term Investment? Based on Text Analysis and Machine Learning[J]. Management World, 37(5): 139-156.
黄栋, (2024). 智能投顾发展与ChatGPT工具的应用[J]. 金融科技时代, 32(3): 75-79.
Huang D, (2024). Development of Intelligent Investment and Application of ChatGPT Tool[J]. FinTech Time, 32(3): 75-79.
姜富伟, 孟令超, 唐国豪, (2021). 媒体文本情绪与股票回报预测[J]. 经济学(季刊), 21(4): 1323-1344.
Jiang F W, Meng L C, Tang G H, (2021). Media Textual Sentiment and Chinese Stock Return Predictability[J]. China Economic Quarterly, 21(4): 1323-1344.
姜富伟, 刘雨旻, 孟令超, (2024). 大语言模型、文本情绪与金融市场[J]. 管理世界, 40(8): 42-64.
Jiang F W, Liu Y M, Meng L C, (2024). Large Language Model and Textual Sentiment Analysis in Chinese Stock Markets[J]. Management World, 40(8): 42-64.
廖理, (2021). 另类数据: 经济增长的新亮点[J]. 人民论坛·学术前沿, (6): 22-27.
Liao L, (2021). Alternative Data: A New Area of Economic Growth[J]. People's Forum: Academic Frontier, (6): 22-27.
林耀虎, 刘善存, 杨海军, (2022). 一种基于机器学习和蜡烛图的股市投资策略研究[J]. 计量经济学报, 2(1): 126-140.
Lin Y H, Liu S C, Yang H J, (2022). A Novel Stock Investment Strategy Using Fusion of Machine Learning Techniques and Candlestick Charting[J]. China Journal of Econometrics, 2(1): 126-140.
汪昌云, 武佳薇, (2015). 媒体语气、投资者情绪与IPO 定价[J]. 金融研究, (9): 174-189.
Wang C Y, Wu J W, (2015). Media Tone, Investor Sentiment and IPO Pricing[J]. Journal of Financial Research, (9): 174-189.
汪寿阳, 李明琛, 杨昆, 林文灿, 姜尚荣, 等, (2023). ChatGPT+ 金融: 八个值得关注的研究方向与问题[J]. 管理评论, 35(4): 3-11.
Wang S Y, Li M C, Yang K, Lin W C, Jiang S R, et al. (2023). ChatGPT + Finance: Eight Noteworthy Research Directions and Issues[J]. Management Review, 35(4): 3-11.
许雪晨, 田侃, (2021). 一种基于金融文本情感分析的股票指数预测新方法[J]. 数量经济技术经济研究, 38(12): 124-145.
Xu X C, Tian K, (2021). A Novel Financial Text Sentiment Analysis-based Approach for Stock Index Prediction[J]. Quantitative Economics and Technical Economics Research, 38(12): 124-145.
姚加权, 冯绪, 王赞钧, 纪荣嵘, 张维, (2021). 语调、情绪及市场影响: 基于金融情绪词典[J]. 管理科学学报, 24(5): 26-46.
Yao J Q, Feng X, Wang Z J, Ji R R, Zhang W, (2021). Tone, Sentiment and Market Impacts: The Construction of Chinese Sentiment Dictionary in Finance[J]. Journal of Managemenr Sciences in China, 24(5): 26-46.
张一帆, 林建浩, 樊嘉诚, (2023). 新闻文本大数据与消费增速实时预测——基于叙事经济学的视角[J]. 金融研究, (5): 152-169.
Zhang Y F, Lin J H, Fan J C, (2023). News Data and Real-Time Consumption Growth Projections: A View from Narrative Economics[J]. Journal of Financial Research, (5): 152-169.
Abideen Z U I, Ahmed Z, Qiu H, Zhao Y W, (2023). Do Behavioral Biases Affect Investors' Investment Decision Making? Evidence From the Pakistani Equity Market[J]. Risks, 11(6): 109.
Chen J, Tang G H, Zhou G F, Zhu W, (2023). ChatGPT, Stock Market Predictability and Links to the Macroeconomy[J]. Olin Business School Center for Finance & AccountingResearch Paper, (2023/18).
Cowles A, (1933). Can Stock Market Forecasters Forecast?[J]. Econometrica: Journal of the Econometric Society, 1(3): 309-324.
Grossman S J, Stiglitz J E, (1980). On the Impossibility of Informationally Efficient Markets[J]. The American Economic Review, 70(3): 393-408.
He K, Zhang X, Ren S, Sun J, (2016). Deep Residual Learning for Image Recognition[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition: 770-778.
Jiang J, Kelly B, Xiu D, (2023). (Re-) Imag (in) Ing Price Trends[J]. The Journal of Finance, 78(6): 3193-3249.
Kaelbling L P, Littman M L, Moore A W, (1996). Reinforcement Learning: A Survey[J]. Journal of Artificial Intelligence Research, 4: 237-285.
Kim A, Muhn M, Nikolaev V, (2024). Financial Statement Analysis with Large Language Models[J]. arXiv Preprint: 2407.17866.
Kipf T N, Welling M, (2016). Semi-supervised Classification with Graph Convolutional Networks[J]. arXiv Preprint: 1609.02907.
Liu H, Sferrazza C, Abbeel P, (2023a). Languages are Rewards: Hindsight Finetuning Using Human Feedback[J]. arXiv Preprint: 2302.02676.
Liu R, Yang R, Jia C, Zhang G, Zhou D, et al. (2023b). Training Socially Aligned Language Models in Simulated Human Society[J]. arXiv Preprint: 2305.16960. %
Lo A W, (2004). The Adaptive Markets Hypothesis: Market Efficiency from an Evolutionary Perspective[J]. Journal of Portfolio Management, Forthcoming.
Lopez-Lira A, Tang Y, (2023). Can ChatGPT Forecast Stock Price Movements? Return Predictability and Large Language Models[J]. arXiv Preprint: 2304.07619.
Mohamed Rida S, Hamza E, Taher Z, (2024). From Technical Indicators to Trading Decisions: A Deep Learning Model Combining CNN and LSTM[J]. International Journal of Advanced Computer Science & Applications, 15(6): 847-855.
Noda A, (2021). On the Evolution of Cryptocurrency Market Efficiency[J]. Applied Economics Letters, 28(6): 433-439.
Obaid K, Pukthuanthong K, (2022). A Picture is Worth a Thousand Words: Measuring Investor Sentiment by Combining Machine Learning and Photos from News[J]. Journal of Financial Economics, 144(1): 273-297.
Omeiza D, Speakman S, Cintas C, Weldermariam K, (2019). Smooth Grad-CAM++: An Enhanced Inference Level Visualization Technique for Deep Convolutional Neural Network Models[J]. arXiv Preprint: 1908.01224.
Park J S, O'Brien J, Cai C J, Morris M R, Liang P, et al. (2023). Generative Agents: Interactive Simulacra of Human Behavior[C]// Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology: 1-22. %
Radford A, Sutskever I, Kim J W, Krueger G, Agarwal S, (2021). CLIP: Connecting Text and Images[J]. Openai.com.
Ribeiro C, (2002). Reinforcement Learning Agents[J]. Artificial Intelligence Review, 17: 223-250.
Rossi E, Chamberlain B, Frasca F, et al. (2020). Temporal graph networks for deep learning on dynamic graphs[J]. arXiv preprint arXiv: 2020.10637.
Sim H S, Kim H I, Ahn J J, (2019). Is Deep Learning for Image Recognition Applicable to Stock Market Prediction?[J]. Complexity, 2019(1): 4324878.
Taylor M E, Stone P, (2009). Transfer Learning for Reinforcement Learning Domains: A Survey[J]. Journal of Machine Learning Research, 10(7): 1633-1685.
Tetlock P C, (2007). Giving Content to Investor Sentiment: The Role of Media in the Stock Market[J]. The Journal of finance, 62(3): 1139-1168.
Tirinzoni A, Sessa A, Pirotta M, Restelli M, (2018). Importance Weighted Transfer of Samples in Reinforcement Learning[C]// International Conference on Machine Learning, PMLR 80: 4936-4945.
Wang Y, Zhong W, Li L, Mi F, Zeng X, et al. (2023a). Aligning Large Language Models with Human: A Survey[J]. arXiv Preprint: 2307.12966.
Wang Z, Zhang G, Yang K, Shi N, Zhou W, et al. (2023b). Interactive Natural Language Processing[J]. arXiv Preprint: 2305.13246.
Wei J, Wang X, Schuurmans D, Bosma M, Xia F, et al. (2022). Chain-of-thought Prompting Elicits Reasoning in Large Language Models[J]. Advances in Neural Information Processing Systems, 35: 24824-24837.
Xi Z, Chen W, Guo X, He W, Ding Y, et al. (2023). The Rise and Potential of Large Language Model Based Agents: A Survey[J]. arXiv Preprint: 2309.07864.
Xia Y, Wang R, Liu X, Li M, Yu T, et al. (2024). Beyond Chain-of-thought: A Survey of Chain-of-x Paradigms for Llms[J]. arXiv Preprint: 2404.15676.
Yang H, Zhang B, Wang N, Guo C, Zhang X, et al. (2024). Finrobot: An Open-Source AI Agent Platform for Financial Applications Using Large Language Models[J]. arXiv Preprint: 2405.14767.
Yang Q, Liu Y, Chen T, Tong Y, (2019). Federated Machine Learning: Concept and Applications[J]. ACM Transactions on Intelligent Systems and Technology (TIST), 10(2): 1-19.
Yu Y, Li H, Chen Z, Jiang Y, Li Y, et al. (2024). Finmem: A Performance-enhanced LLM Trading Agent with Layered Memory and Character Design[C]// Proceedings of the AAAI Symposium Series, 3(1): 595-597.
Yuan A, Coenen A, Reif E, Ippolito D, (2022). Wordcraft: Story Writing with Large Language Models[C]// Proceedings of the 27th International Conference on Intelligent User Interfaces: 841-852.
Zhang W, Zhao L, Xia H, Sun S, Sun J, et al. (2024). A Multimodal Foundation Agent for Financial Trading: Tool-augmented, Diversified, and Generalist[C]// Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining: 4314-4325.
Zhu Y, Jiang Z, Li B, (2017). Deep Reinforcement Learning for Portfolio Management[C]// Proceedings of the International Conference on Machine Learning (ICML). Sydney, Australia.
Zhu Z, Zhu K, (2024). Enhancement of Price Trend Trading Strategies via Image-induced Importance Weights[J]. arXiv Preprint: 2408.08483.

Funding

National Natural Science Foundation of China (12171282)

RIGHTS & PERMISSIONS

Editorial Office of the China Journal of Econometrics, 2025, All rights reserved. Unauthorized reproduction is prohibited.
PDF(1542 KB)

491

Accesses

0

Citation

Detail

Sections
Recommended

/