Open Access Open Access  Restricted Access Subscription Access

MULTI-AGENT FINANCIAL STATEMENT ANALYSIS SYSTEM

Midhun Kumar V, Mr. Subramanian E, Nikitha M, Rohit R

Abstract


Financial statement analysis traditionally requires considerable manual effort to extract financial information, calculate ratios, assess risks, and prepare comprehensive reports. This paper presents a Multi-Agent Financial Statement Analysis System that automates these activities using Large Language Models, Retrieval-Augmented Generation, and specialized analytical agents. The system processes financial statement PDFs, extracts relevant information, stores document representations in a vector database, and retrieves contextual information for analysis. Dedicated agents perform financial metric extraction, ratio analysis, risk assessment, competitor analysis, SWOT analysis, and investment research report generation. The proposed approach provides a structured workflow for transforming financial documents into an integrated financial analysis.


Full Text:

PDF

References


. Chen, Z., Chen, W., et al. (2021). FinQA: A Dataset of Numerical Reasoning over Financial Data. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing.

. Lewis, P., Perez, E., Piktus, A., et al. (2020). Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. Advances in Neural Information Processing Systems.

. Yang, H., Liu, X.-Y.; Wang, C. D. (2023). FinGPT: Open-Source Financial Large Language Models. arXiv preprint.

. Guo, T., Chen, X., Wang, Y., et al. (2024). Large Language Model Based Multi-Agents: A Survey of Progress and Challenges. Proceedings of the International Joint Conference on Artificial Intelligence.

. Li, X., et al. (2024). A Survey on LLM-based Multi-Agent Systems: Workflow, Infrastructure, and Challenges. arXiv preprint.

. Vaswani, A., et al. (2017). Attention Is All You Need. Advances in Neural Information Processing Systems.

. Reimers, N.; Gurevych, I. (2019). Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. Proceedings of EMNLP-IJCNLP.

. Devlin, J., Chang, M.-W., Lee, K.; Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. Proceedings of NAACL-HLT.


Refbacks

  • There are currently no refbacks.