2000 character limit reached
Modal-adaptive Knowledge-enhanced Graph-based Financial Prediction from Monetary Policy Conference Calls with LLM (2403.16055v4)
Published 24 Mar 2024 in cs.CE
Abstract: Financial prediction from Monetary Policy Conference (MPC) calls is a new yet challenging task, which targets at predicting the price movement and volatility for specific financial assets by analyzing multimodal information including text, video, and audio. Although the existing work has achieved great success using cross-modal transformer blocks, it overlooks the potential external financial knowledge, the varying contributions of different modalities to financial prediction, as well as the innate relations among different financial assets. To tackle these limitations, we propose a novel Modal-Adaptive kNowledge-enhAnced Graph-basEd financial pRediction scheme, named MANAGER. Specifically, MANAGER resorts to FinDKG to obtain the external related knowledge for the input text. Meanwhile, MANAGER adopts BEiT-3 and Hidden-unit BERT (HuBERT) to extract the video and audio features, respectively. Thereafter, MANAGER introduces a novel knowledge-enhanced cross-modal graph that fully characterizes the semantic relations among text, external knowledge, video and audio, to adaptively utilize the information in different modalities, with ChatGLM2 as the backbone. Extensive experiments on a publicly available dataset Monopoly verify the superiority of our model over cutting-edge methods.
- Ellyn R. Boukus and Joshua V. Rosenberg. 2006. The information content of fomc minutes. Monetary Economics.
- Language models are few-shot learners. ArXiv.
- It’s not always about the money, sometimes it’s about sending a message: Evidence of informational content in monetary policy announcements.
- Longbing Cao. 2021. Ai in finance: Challenges, techniques, and opportunities. ACM Computing Surveys (CSUR).
- Forecasting stock market crisis events using deep and statistical machine learning techniques. Expert Syst. Appl.
- BERT: pre-training of deep bidirectional transformers for language understanding. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4171–4186. ACL.
- Ning Du and David V. Budescu. 2007. Does past volatility affect investors’ price forecasts and confidence judgements? International Journal of Forecasting.
- Glm: General language model pretraining with autoregressive blank infilling. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, pages 320–335.
- Improving multimodal fusion with hierarchical mutual information maximization for multimodal sentiment analysis. ArXiv.
- Hubert: Self-supervised speech representation learning by masked prediction of hidden units. IEEE/ACM Transactions on Audio, Speech, and Language Processing.
- Lora: Low-rank adaptation of large language models. ArXiv.
- Weiwei Jiang. 2020. Applications of deep learning in stock market prediction: recent progress. Expert Syst. Appl.
- Multi-source semantic graph-based multimodal sarcasm explanation generation. In Annual Meeting of the Association for Computational Linguistics. ACL.
- Thomas N. Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In International Conference on Learning Representations. OpenReview.net.
- Katharina Lewellen. 2003. Financing decisions when managers are risk averse. MIT Sloan School of Management Working Paper Series.
- Xiaohui Victor Li. 2023. Findkg: Dynamic knowledge graph with large language models for global finance. pages 1–64. SSRN.
- Vivian Liu and Lydia B. Chilton. 2021. Design guidelines for prompt engineering text-to-image generative models. Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems.
- Finbert: A pre-trained financial language representation model for financial text mining. In Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, IJCAI-20, pages 4513–4519. International Joint Conferences on Artificial Intelligence Organization.
- Ilya Loshchilov and Frank Hutter. 2017. Fixing weight decay regularization in adam. CoRR, abs/1711.05101.
- Monopoly: Financial prediction from monetary policy conference videos using multimodal cues. Proceedings of the 30th ACM International Conference on Multimedia.
- Sentiment-enhanced graph-based sarcasm explanation in dialogue. CoRR, abs/2402.03658.
- Training language models to follow instructions with human feedback. ArXiv.
- Context-dependent sentiment analysis in user-generated videos. In Annual Meeting of the Association for Computational Linguistics.
- Yu Qin and Yi Yang. 2019. What you say and how you say it matters: Predicting stock volatility using verbal and vocal cues. In Annual Meeting of the Association for Computational Linguistics.
- Multimodal multi-speaker merger & acquisition financial modeling: A new task, dataset, and neural baselines. In Annual Meeting of the Association for Computational Linguistics.
- Multimodal multi-task financial risk forecasting. Proceedings of the 28th ACM International Conference on Multimedia.
- Adam Hale Shapiro and Daniel J. Wilson. 2019. Taking the fed at its word: A new approach to estimating central bank objectives using text analysis. Federal Reserve Bank of San Francisco, Working Paper Series.
- Mlp-mixer: An all-mlp architecture for vision. In Neural Information Processing Systems.
- Multimodal transformer for unaligned multimodal language sequences. Proceedings of the conference. Association for Computational Linguistics. Meeting.
- Fingpt: Instruction tuning benchmark for open-source large language models in financial datasets. ArXiv.
- Fingpt: Instruction tuning benchmark for open-source large language models in financial datasets. NeurIPS Workshop on Instruction Tuning and Instruction Following.
- Image as a foreign language: Beit pretraining for all vision and vision-language tasks. CoRR, abs/2208.10442.
- A prompt pattern catalog to enhance prompt engineering with chatgpt. ArXiv.
- Autogen: Enabling next-gen llm applications via multi-agent conversation framework. ArXiv.
- Bloomberggpt: A large language model for finance. ArXiv.
- Html: Hierarchical transformer-based multi-task learning for volatility prediction. Proceedings of The Web Conference 2020.
- Hubert-ee: Early exiting hubert for efficient speech recognition. ArXiv.
- Shui-Ling Yu and Zhe Li. 2018. Forecasting stock price index volatility with lstm deep neural network.
- Yixuan Zhang and Haonan Li. 2023. Can large langauge model comprehend ancient chinese? a preliminary test on aclue. In International Conference on Algebraic and Logic Programming.