TY - GEN
T1 - Designing Trading Strategies with LLMs
T2 - 21st International Conference on Intelligent Computing, ICIC 2025
AU - Wu, Jinheng
AU - Zhang, Di
AU - Niu, Qiang
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.
PY - 2025/7/26
Y1 - 2025/7/26
N2 - Large Language Models (LLMs) offer a promising approach to enhancing traditional financial tools with intuitive interfaces. However, in financial trading, particularly in Exchange-Traded Fund (ETF) strategies, the need for precision, interpretability, and reliability limits their direct application due to challenges like inefficiencies and hallucinations. This study introduces a two-stage framework that uses a domain-specific language (DSL) as an intermediary. Natural language inputs are converted into DSL through in-context learning (ICL) and then translated into general-purpose programming languages. This method improves computational efficiency, reduces manual intervention, and ensures clear interpretability. Experiments show the framework achieves a 95.3% match rate in mapping trading logic to DSL. The study also explores the impact of DSL design and LLM selection, demonstrating the framework's applicability beyond finance. By integrating ICL and DSL, this framework offers a scalable, cost-effective solution for linking natural language processing with financial strategy execution, advancing automated trading systems.
AB - Large Language Models (LLMs) offer a promising approach to enhancing traditional financial tools with intuitive interfaces. However, in financial trading, particularly in Exchange-Traded Fund (ETF) strategies, the need for precision, interpretability, and reliability limits their direct application due to challenges like inefficiencies and hallucinations. This study introduces a two-stage framework that uses a domain-specific language (DSL) as an intermediary. Natural language inputs are converted into DSL through in-context learning (ICL) and then translated into general-purpose programming languages. This method improves computational efficiency, reduces manual intervention, and ensures clear interpretability. Experiments show the framework achieves a 95.3% match rate in mapping trading logic to DSL. The study also explores the impact of DSL design and LLM selection, demonstrating the framework's applicability beyond finance. By integrating ICL and DSL, this framework offers a scalable, cost-effective solution for linking natural language processing with financial strategy execution, advancing automated trading systems.
UR - https://www.scopus.com/pages/publications/105012820316
U2 - 10.1007/978-981-96-9891-2_24
DO - 10.1007/978-981-96-9891-2_24
M3 - Conference Proceeding
AN - SCOPUS:105012820316
SN - 9789819698905
T3 - Lecture Notes in Computer Science
SP - 278
EP - 291
BT - Advanced Intelligent Computing Technology and Applications - 21st International Conference, ICIC 2025, Proceedings
A2 - Huang, De-Shuang
A2 - Li, Bo
A2 - Chen, Haiming
A2 - Zhang, Chuanlei
PB - Springer Science and Business Media Deutschland GmbH
Y2 - 26 July 2025 through 29 July 2025
ER -