FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design

Authors

  • Yangyang Yu Stevens Institute of Technology
  • Haohang Li Stevens Institute of Technology
  • Zhi Chen Stevens Institute of Technology
  • Yuechen Jiang Stevens Institute of Technology
  • Yang Li Stevens Institute of Technology
  • Denghui Zhang Stevens Institute of Technology
  • Rong Liu Stevens Institute of Technology
  • Jordan W. Suchow Stevens Institute of Technology
  • Khaldoun Khashanah Stevens Institute of Technology

DOI:

https://doi.org/10.1609/aaaiss.v3i1.31290

Keywords:

Financial AI, Large Language Models, Trading Algorithms, Generative AI, Cognitive Science, Financial Technology

Abstract

Recent advancements in Large Language Models (LLMs) have exhibited notable efficacy in question-answering (QA) tasks across diverse domains. Their prowess in integrating extensive web knowledge has fueled interest in developing LLM-based autonomous agents. While LLMs are efficient in decoding human instructions and deriving solutions by holistically processing historical inputs, transitioning to purpose-driven agents requires a supplementary rational architecture to process multi-source information, establish reasoning chains, and prioritize critical tasks. Addressing this, we introduce FinMem, a novel LLM-based agent framework devised for financial decision-making. It encompasses three core modules: Profiling, to customize the agent's characteristics; Memory, with layered message processing, to aid the agent in assimilating hierarchical financial data; and Decision-making, to convert insights gained from memories into investment decisions. Notably, FinMem's memory module aligns closely with the cognitive structure of human traders, offering robust interpretability and real-time tuning. Its adjustable cognitive span allows for the retention of critical information beyond human perceptual limits, thereby enhancing trading outcomes. This framework enables the agent to self-evolve its professional knowledge, react agilely to new investment cues, and continuously refine trading decisions in the volatile financial environment. We first compare FinMem with various algorithmic agents on a scalable real-world financial dataset, underscoring its leading trading performance in stocks. We then fine-tuned the agent's perceptual span and character setting to achieve a significantly enhanced trading performance. Collectively, FinMem presents a cutting-edge LLM agent framework for automated trading, boosting cumulative investment returns.
AAAI Spring Symposium 2024 Proceedings Cover

Downloads

Published

2024-05-20

How to Cite

Yu, Y., Li, H., Chen, Z., Jiang, Y., Li, Y., Zhang, D., Liu, R., Suchow, J. W., & Khashanah, K. (2024). FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design. Proceedings of the AAAI Symposium Series, 3(1), 595-597. https://doi.org/10.1609/aaaiss.v3i1.31290

Issue

Vol. 3 No. 1: Proceedings of the 2024 AAAI Spring Symposium Series

Section

Symposium on Human-Like Learning