Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
41 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
41 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

AMA-LSTM: Pioneering Robust and Fair Financial Audio Analysis for Stock Volatility Prediction (2407.18324v1)

Published 3 Jul 2024 in cs.LG, cs.CL, eess.AS, q-fin.CP, and q-fin.ST

Abstract: Stock volatility prediction is an important task in the financial industry. Recent advancements in multimodal methodologies, which integrate both textual and auditory data, have demonstrated significant improvements in this domain, such as earnings calls (Earnings calls are public available and often involve the management team of a public company and interested parties to discuss the company's earnings). However, these multimodal methods have faced two drawbacks. First, they often fail to yield reliable models and overfit the data due to their absorption of stochastic information from the stock market. Moreover, using multimodal models to predict stock volatility suffers from gender bias and lacks an efficient way to eliminate such bias. To address these aforementioned problems, we use adversarial training to generate perturbations that simulate the inherent stochasticity and bias, by creating areas resistant to random information around the input space to improve model robustness and fairness. Our comprehensive experiments on two real-world financial audio datasets reveal that this method exceeds the performance of current state-of-the-art solution. This confirms the value of adversarial training in reducing stochasticity and bias for stock volatility prediction tasks.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize File Document Download Save Streamline Icon: https://streamlinehq.com PDF File Document Download Save Streamline Icon: https://streamlinehq.com Markdown Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (45)
  1. Dogu Araci. 2019. Finbert: Financial sentiment analysis with pre-trained language models. arXiv preprint arXiv:1908.10063.
  2. Anish Athalye and Nicholas Carlini. 2018. On the robustness of the cvpr 2018 white-box adversarial example defenses. arXiv preprint arXiv:1804.03286.
  3. Skirting the issues: Experimental evidence of gender bias in ipo prospectus evaluations. Journal of Management, 40(6):1732–1759.
  4. Do sophisticated investors interpret earnings conference call tone differently than investors at large? evidence from short sales. Journal of Corporate Finance, 31:203–219.
  5. Paul Boersma and Vincent Van Heuven. 2001. Speak and unspeak with praat. Glot International, 5(9/10):341–347.
  6. Quantitative and descriptive comparison of four acoustic analysis systems: Vowel measurements.
  7. Nicholas Carlini and David Wagner. 2018. Audio adversarial examples: Targeted attacks on speech-to-text. In 2018 IEEE security and privacy workshops (SPW), pages 1–7. IEEE.
  8. The role of gender in the aggressive questioning of ceos during earnings conference calls. The Accounting Review, 97(7):79–107.
  9. Fairness measures for machine learning in finance. The Journal of Financial Data Science.
  10. Adversarial audio synthesis. arXiv preprint arXiv:1802.04208.
  11. Equilibrium portfolio strategies in the presence of sentiment risk and excess volatility. The Journal of Finance, 64(2):579–629.
  12. Enhancing stock movement prediction with adversarial training. In Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI-19, pages 5843–5849. International Joint Conferences on Artificial Intelligence Organization.
  13. The sound of (in) sincerity. Journal of Pragmatics, 121:147–161.
  14. Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572.
  15. Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural computation, 9(8):1735–1780.
  16. Learning with a strong adversary. arXiv preprint arXiv:1511.03034.
  17. A prediction approach for stock market volatility based on time series data. IEEE Access, 7:17287–17298.
  18. Predicting risk from financial reports with regression. In Proceedings of human language technologies: the 2009 annual conference of the North American Chapter of the Association for Computational Linguistics, pages 272–280.
  19. Volatility forecast using hybrid neural network models. Expert Systems with Applications, 41(5):2437–2442.
  20. Maec: A multimodal aligned earnings conference call dataset for financial risk prediction. In Proceedings of the 29th ACM International Conference on Information & Knowledge Management, pages 3063–3070.
  21. Towards deep learning models resistant to adversarial attacks. arXiv preprint arXiv:1706.06083.
  22. Diverse audio captioning via adversarial training. In ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 8882–8886. IEEE.
  23. Adversarial training methods for semi-supervised text classification. arXiv preprint arXiv:1605.07725.
  24. Sentiment analysis on social media for stock movement prediction. Expert Systems with Applications, 42(24):9603–9611.
  25. A gender bias in the acoustic-melodic features of charismatic speech? In Proceedings of the International Conference on Spoken Language Processing, pages 2248–2252. International Speech Communication Association.
  26. Context-dependent sentiment analysis in user-generated videos. In Proceedings of the 55th annual meeting of the association for computational linguistics (volume 1: Long papers), pages 873–883.
  27. Yu Qin and Yi Yang. 2019. What you say and how you say it matters: Predicting stock volatility using verbal and vocal cues. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 390–401.
  28. Volatility prediction using financial disclosures sentiments with word embedding-based ir models. arXiv preprint arXiv:1702.01978.
  29. An empirical investigation of bias in the multimodal analysis of financial earnings calls. In Proceedings of the 2021 conference of the North American chapter of the association for computational linguistics: human language technologies, pages 3751–3757.
  30. Multimodal multi-speaker merger & acquisition financial modeling: A new task, dataset, and neural baselines. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 6751–6762.
  31. Voltage: Volatility forecasting via text audio fusion with graph convolution networks for earnings calls. In Proceedings of the 2020 conference on empirical methods in natural language processing (EMNLP), pages 8001–8013.
  32. Understanding adversarial training: Increasing local stability of supervised models through robust optimization. Neurocomputing, 307:195–204.
  33. Training augmentation with adversarial examples for robust speech recognition. arXiv preprint arXiv:1806.02782.
  34. Harini Suresh and John V Guttag. 2019. A framework for understanding unintended consequences of machine learning. arXiv preprint arXiv:1901.10002, 2(8).
  35. Intriguing properties of neural networks. arXiv preprint arXiv:1312.6199.
  36. Is image encoding beneficial for deep learning in finance? IEEE Internet of Things Journal, 9(8):5617–5628.
  37. Alerta-net: A temporal distance-aware recurrent networks for stock movement and volatility prediction. In Proceedings of the International Conference on Advances in Social Networks Analysis and Mining, pages 538–542.
  38. Stock movement and volatility prediction from tweets, macroeconomic factors and historical prices. In 2023 IEEE International Conference on Big Data (BigData), pages 1863–1872. IEEE.
  39. A word is worth a thousand dollars: Adversarial attack on tweets fools stock prediction. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 587–599, Seattle, United States. Association for Computational Linguistics.
  40. Html: Hierarchical transformer-based multi-task learning for volatility prediction. In Proceedings of The Web Conference 2020, pages 441–451.
  41. Explainable text-driven neural network for stock prediction. In 2018 5th IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS), pages 441–445. IEEE.
  42. Bridge the gap between cv and nlp! a gradient-based textual adversarial attack framework. arXiv preprint arXiv:2110.15317.
  43. Word-level textual adversarial attacking as combinatorial optimization. arXiv preprint arXiv:1910.12196.
  44. Predicting stock market volatility based on textual sentiment: A nonlinear analysis. Journal of Forecasting, 40(8):1479–1500.
  45. Improving stock market prediction via heterogeneous information fusion. Knowledge-Based Systems, 143:236–247.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (8)
  1. ShengKun Wang (8 papers)
  2. Taoran Ji (12 papers)
  3. Jianfeng He (32 papers)
  4. Mariam Almutairi (2 papers)
  5. Dan Wang (154 papers)
  6. Linhan Wang (10 papers)
  7. Min Zhang (630 papers)
  8. Chang-Tien Lu (54 papers)
Citations (2)
View on Semantic Scholar
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets