Automating Investment Suitability Checks with LLM-Driven Semantic Similarity and Siamese Networks
Keywords:
investment suitability, MiFID II, FINRA, Large Language Models, Siamese Neural Networks, semantic similarity, transformer embeddingsAbstract
This MiFID II and FINRA-compliant research automates investment appropriateness assessments using LLMs and SNNs. Transformer-based Siamese network embeddings check LLM-generated financial advice for investor risk profile semantics. To increase auditability and traceability, financial recommendation alignment with appropriateness matrices is checked twice. The suggested technique is more scalable and flexible than rule-based appropriateness engines for different investor profiles and regulations, according to experiments. To test model efficacy, semantic similarity, precision-recall, and regulatory compliance alignment are evaluated. Results suggest LLM-driven design and Siamese similarity validation may enhance automated, compliant, and interpretable financial advice systems.
Downloads
References
M. K. Braverman, A. Cohen, and R. R. Dyer, “Artificial Intelligence in Financial Regulation: A Risk-Based Supervisory Perspective,” Journal of Financial Regulation and Compliance, vol. 31, no. 2, pp. 145–162, 2023.
European Securities and Markets Authority (ESMA), MiFID II: Markets in Financial Instruments Directive (Directive 2014/65/EU), Official Journal of the European Union, 2018.
Financial Industry Regulatory Authority (FINRA), Suitability Rule 2111: Know Your Customer and Suitability Obligations, Washington D.C., 2021.
S. Hochreiter and J. Schmidhuber, “Long Short-Term Memory,” Neural Computation, vol. 9, no. 8, pp. 1735–1780, 1997.
A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, and I. Polosukhin, “Attention Is All You Need,” in Proc. Advances in Neural Information Processing Systems (NeurIPS), 2017, pp. 5998–6008.
OpenAI, GPT-4 Technical Report, OpenAI, San Francisco, CA, 2023.
J. Devlin, M. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,” in Proc. NAACL-HLT, 2019, pp. 4171–4186.
D. Reimers and I. Gurevych, “Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks,” in Proc. EMNLP-IJCNLP, 2019, pp. 3982–3992.
A. Doshi-Velez and B. Kim, “Towards a Rigorous Science of Interpretable Machine Learning,” arXiv preprint arXiv:1702.08608, 2017.
S. Lundberg and S. Lee, “A Unified Approach to Interpreting Model Predictions,” in Proc. Advances in Neural Information Processing Systems (NeurIPS), 2017, pp. 4765–4774.
A. Turing, “Computing Machinery and Intelligence,” Mind, vol. 59, no. 236, pp. 433–460, 1950.
R. Ramaswamy, C. Sarkar, and S. S. Varanasi, “Explainable AI for Regulatory Compliance in Financial Services,” IEEE Transactions on Computational Social Systems, vol. 10, no. 2, pp. 498–509, 2023.
Y. Zhang, H. Wang, and X. Liu, “Siamese Neural Networks for Semantic Similarity Detection in Financial Text,” Expert Systems with Applications, vol. 211, pp. 118544, 2023.
M. Bommasani et al., “On the Opportunities and Risks of Foundation Models,” arXiv preprint arXiv:2108.07258, 2021.
N. Ghosh and P. Shukla, “Automated Compliance Monitoring using Transformer-Based Language Models,” Journal of Financial Data Science, vol. 5, no. 1, pp. 1–20, 2023.
M. Hendrycks, C. Burns, S. Basart, A. Zou, and D. Song, “Measuring Massive Multitask Language Understanding,” in Proc. International Conference on Learning Representations (ICLR), 2021.
S. Li, P. Xu, and H. Yang, “Contrastive Representation Learning for Legal Textual Similarity,” IEEE Access, vol. 10, pp. 115672–115683, 2022.
J. Zhao, R. Jin, and Y. Liu, “Trustworthy AI Systems for Financial Decision-Making: Challenges and Directions,” ACM Computing Surveys, vol. 56, no. 3, pp. 1–42, 2024.
A. Srivastava, A. J. Lee, and D. P. Deisenroth, “Explainable Reinforcement Learning for Automated Financial Advisory Systems,” IEEE Transactions on Neural Networks and Learning Systems, vol. 34, no. 9, pp. 5186–5201, 2023.
A. Huang, S. M. Chen, and M. A. Walker, “AI in Banking and Financial Markets: Opportunities, Challenges, and Regulatory Implications,” Harvard Business Review Analytic Services Report, 2022.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
