FinSphere, a Real-Time Stock Analysis Agent Powered by Instruction-Tuned LLMs and Domain Tools
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915378665357312 |
|---|---|
| author | Han, Shijie Zhang, Jingshu Shen, Yiqing Yan, Kaiyuan Li, Hongguang |
| author_facet | Han, Shijie Zhang, Jingshu Shen, Yiqing Yan, Kaiyuan Li, Hongguang |
| contents | Current financial large language models (FinLLMs) struggle with two critical limitations: the absence of objective evaluation metrics to assess the quality of stock analysis reports and a lack of depth in stock analysis, which impedes their ability to generate professional-grade insights. To address these challenges, this paper introduces FinSphere, a stock analysis agent, along with three major contributions: (1) AnalyScore, a systematic evaluation framework for assessing stock analysis quality, (2) Stocksis, a dataset curated by industry experts to enhance LLMs' stock analysis capabilities, and (3) FinSphere, an AI agent that can generate high-quality stock analysis reports in response to user queries. Experiments demonstrate that FinSphere achieves superior performance compared to both general and domain-specific LLMs, as well as existing agent-based systems, even when they are enhanced with real-time data access and few-shot guidance. The integrated framework, which combines real-time data feeds, quantitative tools, and an instruction-tuned LLM, yields substantial improvements in both analytical quality and practical applicability for real-world stock analysis. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_12399 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FinSphere, a Real-Time Stock Analysis Agent Powered by Instruction-Tuned LLMs and Domain Tools Han, Shijie Zhang, Jingshu Shen, Yiqing Yan, Kaiyuan Li, Hongguang Artificial Intelligence Computation and Language Information Retrieval Computational Finance Current financial large language models (FinLLMs) struggle with two critical limitations: the absence of objective evaluation metrics to assess the quality of stock analysis reports and a lack of depth in stock analysis, which impedes their ability to generate professional-grade insights. To address these challenges, this paper introduces FinSphere, a stock analysis agent, along with three major contributions: (1) AnalyScore, a systematic evaluation framework for assessing stock analysis quality, (2) Stocksis, a dataset curated by industry experts to enhance LLMs' stock analysis capabilities, and (3) FinSphere, an AI agent that can generate high-quality stock analysis reports in response to user queries. Experiments demonstrate that FinSphere achieves superior performance compared to both general and domain-specific LLMs, as well as existing agent-based systems, even when they are enhanced with real-time data access and few-shot guidance. The integrated framework, which combines real-time data feeds, quantitative tools, and an instruction-tuned LLM, yields substantial improvements in both analytical quality and practical applicability for real-world stock analysis. |
| title | FinSphere, a Real-Time Stock Analysis Agent Powered by Instruction-Tuned LLMs and Domain Tools |
| topic | Artificial Intelligence Computation and Language Information Retrieval Computational Finance |
| url | https://arxiv.org/abs/2501.12399 |