Using long short‐term memory neural networks to analyze SEC 13D filings: : A recipe for human and machine interaction
Pages 153 - 163
Summary
We implement an efficient methodology for extracting themes from Securities Exchange Commission 13D filings using aspects of human‐assisted active learning and long short‐term memory (LSTM) neural networks. Sentences from the ‘Purpose of Transaction’ section of each filing are extracted and a randomly chosen subset is labelled based on six filing themes that the existing literature on shareholder activism has shown to have an impact on stock returns. We find that an LSTM neural network that accepts sentences as input performs significantly better, with precision of 77%, than an alternately specified neural network that uses the common bag of words approach. This indicates that both sentence structure and vocabulary are important in classifying SEC 13D filings. Our study has important implications, as it addresses the recent cautions raised in the literature that analysis of finance and accounting‐related text sources should move beyond bag‐of‐words approaches to alternatives that incorporate the analysis of word sense and meaning reflecting context.
References
[1]
Bao, W., Yue, J., & Rao, Y. (2017). A deep learning framework for financial time series using stacked autoencoders and long‐short term memory. PLoS ONE, 12(7), e0180944.
[2]
Cardellino, C., Villata, S., Alonso Alemany, L., Cabrio, E. (2015). Information Extraction with Active Learning: A Case Study in Legal Text. CICLing 2015 ‐Proceedings of the 16th International Conference on Intelligence Text Processing and Computational Linguistics.
[3]
Chan, Y. S., & Ng, H. T. (2007). Domain adaptation with active learning for word sense disambiguation. In A. Zaenen, & A. van den Bosch (Eds.), Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics (pp. 49–56). Stroudsburg, PA, USA: ACL.
[4]
Chen, J., Schein, A., Ungar, L., & Palmer, M. (2006). An empirical study of the behavior of active learning for word sense disambiguation. In Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics: Proceedings of the Main Conference (pp. 120–127). Stroudsburg, PA, USA: ACL.
[5]
Clifford, C. P., & Lindsey, L. A. (2013). Getting what you pay for: blockholder monitoring, CEO compensation, and firm performance. Working paper.
[6]
Cronqvist, H., & Fahlenbrach, R. (2009). Large shareholders and corporate policies. Review of Financial Studies, 22(10), 3941–3976.
[7]
Culotta, A., Kristjansson, T., McCallum, A., & Viola, P. (2006). Corrective feedback and persistent learning for information extraction. Journal of Artificial Intelligence, 170(14), 1101–1122.
[8]
Das, S. R., & Chen, M. Y. (2007). Yahoo! For Amazon: Sentiment extraction from small talk on the web. Management Science, 53(9), 1375–1388.
[9]
El‐Haj, M., Rayson, P., Walker, M., Young, S., & Simaki, V. (2019). In search of meaning: Lessons, resources and next steps for computational analysis of financial discourse. Journal of Business Finance and Accounting, 46(3–4), 265–306.
[10]
Finn, A., & Kushmerick, N. (2003). Active learning selection strategies for information extraction. In Proceedings of the International Workshop on Adaptive Text Extraction and Mining (ATEM‐03), Cavtat–Dubrovnik, Croatia; 18–25.
[11]
Fisher, I., Garnsey, M., & Hughes, M. (2016). Natural language processing in accounting, auditing and finance: A synthesis of the literature with a roadmap for future research. Intelligent Systems in Accounting, Finance and Management, 23, 157–214.
[12]
Goel, S., & Uzuner, O. (2016). Do sentiments matter in fraud detection? Estimating semantic orientation of annual reports. Intelligent Systems in Accounting, Finance and Management, 23(3), 215–239.
[13]
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press. http://www.deeplearningbook.org.
[14]
Hansen, L. K., & Solomon, P. (1990). Neural network ensembles. IEEE Transactions on Pattern Analysis and Machine Intelligence, 12, 993–1001.
[15]
Hoi, S. C. H., Jin, R., & Lyu, M. R. (2006). Large‐scale text categorization by batch mode active learning. In U. K. Scotland, L. Carr, D. D. Roure, A. Iyengar, C. A. Goble, & M. Dahlin (Eds.), Proceedings of the 15th International Conference on World Wide Web, WWW 2006, Edinburgh (pp. 633–642). New York, NY, USA: ACM.
[16]
Holzinger, A. (2016). Interactive Machine Learning for Health Informatics: When Do We Need the Human‐In‐The‐Loop? Brain Informatics. 32: 119–131.
[17]
Jones, R., Ghani, R., Mitchell, T., & Riloff, E. (2003). Active learning for information extraction with multiple view feature sets. In Proceedings of the International Workshop & Tutorial on Adaptive Text Extraction and Mining; 26–33. http://staffwww.dcs.shef.ac.uk/people/F.Ciravegna/ATEM03/ATEM03-Proceedings.pdf
[18]
1Karpoff, J. M., & McWilliams, V. B. (2017). Thirty years of shareholder activism: A survey of empirical research. Journal of Corporate Finance., 44, 405–424.
[19]
Kearney, C., & Liu, S. (2014). Textual sentiment in finance: A survey of methods and models. International Review of Financial Analysis, 33, 171–185.
[20]
Krishnan, C. N. V., Partnoy, F., & Thomas, R. S. (2016). The second wave of hedge fund activism: The importance of reputation, clout, and expertise. Journal of Corporate Finance, 40, 296–314.
[21]
Lewis, D. (1995). A sequential algorithm for training text classifiers: Corrigendum and additional data. ACM SIGIR Forum, 29(2), 13–19.
[22]
Lewis, D. D., & Gale, W. A. (1994). A sequential algorithm for training text classifiers. In B. Croft, & C. J. van Rijsbergen (Eds.), Proceedings of the Seventeenth Annual International ACM‐SIGIR Conference on Research and Development in Information Retrieval (pp. 3–12). New York, NY, USA: ACM/Springer.
[23]
Li, F. (2010). Textual analysis of corporate disclosures: A survey of the literature. Journal of Accounting Literature, 29, 143–165.
[24]
Liere, R., & Tadepalli, P. (1997). Active learning with committees for text categorization. In Proceedings of the Fourteenth National Conference on Artificial Intelligence and Ninth Conference on Innovative Applications of Artificial Intelligence (pp. 591–597). Palo Alto, CA, USA: AAAI Press.
[25]
Lim, Y. (2017). Choice of shareholder activism approach. Working paper. Retrieved from http://fmaconferences.org/SanDiego/Papers/Choice_FMA.pdf.
[26]
Loughran, T., & McDonald, B. (2016). Textual analysis in accounting and finance: A survey. Journal of Accounting Research, 54(4), 1187–1230.
[27]
McCallum, A., & Nigam, K. (1998). Employing EM and pool‐based active learning for text classification. In J. W. Shavlik (Ed.), Proceedings of the 15th International Conference on Machine Learning (ICML‐98) (pp. 350–358). Madison, WI, USA: Morgan Kaufmann.
[28]
Ng, A. (2018). Machine learning yearning: technical strategy for AI engineers, in the era of deep learning (draft version). https://d2wvfoqc9gyqzf.cloudfront.net/content/uploads/2018/09/Ng-MLY01-13.pdf
[29]
Nigam, K., & Ghani, R. (2000). Analyzing the effectiveness and applicability of co‐training. In Proceedings of the Ninth International Conference on Information and Knowledge Management (CIKM 2000) (pp. 86–93). New York, NY, USA: ACM.
[30]
Olsson, F. (2009). A literature survey of active machine learning in the context of natural language processing. SICS Technical Report, 2009:06.
[31]
Partnoy, F. (2015). US hedge fund activism. In J. G. Hill, & R. S. Thomas (Eds.), Research Handbook on Shareholder Power (pp. 99–115). Cheltenham, UK: Edward Elgar.
[32]
Pennington, J., Socher, R., & Manning, C. D. (2014). GloVe: global vectors for word representation. In A. Moschitti, B. Pang, & W. Daelemans (Eds.), Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) (pp. 1532–1543). Stroudsburg, PA, USA: ACL.
[33]
Scheffer, T., Decomain, C., & Wrobel, S. (2001). Active Hidden Markov Models for Information Extraction. In F. Hoffmann, D. Hand, N. M. Adams, D. Fisher, & G. Guimaraes (Eds.), Advances in Intelligent Data Analysis: 4th International Conference, IDA 2001 Cascais, Portugal, September 13–15, 2001 Proceedings. Lecture Notes in Computer Science, 2189. (pp. 309–318). New York, NY, USA: Springer.
[34]
Schohn, G., & Cohn, D. (2000). Less is more: active learning with support vector machines. In P. Langley (Ed.), Proceedings of the Seventeenth International Conference on Machine Learning (ICML‐2000) (pp. 839–846). San Francisco, CA, USA: Morgan Kaufmann.
[35]
Settles, B. (2009). Active learning literature survey. Computer Sciences Technical Report 1648, University of Wisconsin–Madison.
[36]
Tetlock, P. C. (2007). Giving content to investor sentiment: The role of media in the stock market. Journal of Finance, 62, 1139–1168.
[37]
Tong, S., & Koller, D. (2002). Support vector machine active learning with applications to text classification. Journal of Machine Learning Research, 2(March), 45–66.
[38]
Zhu, J., & Hovy, E. (2007). Active learning for word sense disambiguation with methods for addressing the class imbalance problem. In D. Scott, & Uszkoreit (Eds.), Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP–CoNLL) (pp. 783–790). Stroudsburg, PA, USA: ACL.
[39]
Zhu, J., Wang, H., & Hovy, E. (2008). Multi‐criteria‐based strategy to stop active learning for data annotation. In J. Eisner (Ed.), Proceedings of the 22nd International Conference on Computational Linguistics (COLING 2008) (pp. 1129–1136). Manchester, UK: Coling 2008 Organizing Committee.
Index Terms
- Using long short‐term memory neural networks to analyze SEC 13D filings: A recipe for human and machine interaction
Index terms have been assigned to the content through auto-classification.
Recommendations
Using Long Short-Term Memory to Predict Cash Dividend
ICEBT '21: Proceedings of the 2021 5th International Conference on E-Education, E-Business and E-TechnologyInvesting in stocks has been very popular in recent years. Investors hope to make a profit by investing in stocks. However, stock prices are highly volatile. Many investors judge whether to invest in stocks based on historical stock prices, technical ...
Pricing And Hedging Short Sterling Options Using Neural Networks
This paper compares the performance of artificial neural networks (ANNs) with that of the modified Black model in both pricing and hedging short sterling options. Using high-frequency data, standard and hybrid ANNs are trained to generate option prices. ...
Computer Intelligent Value Evaluation Model through ARMA and Long Short-Term Memory Neural Network
AIAM2021: 2021 3rd International Conference on Artificial Intelligence and Advanced ManufactureWith the rapid development of the economy, stocks have become a widely accepted investment option, and professional analysts need to get the latest information to develop investment strategies. According to the efficient market assumption, the incentive ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
October/December 2019
572 pages
© 2020 John Wiley & Sons, Ltd.
Publisher
John Wiley and Sons Ltd.
United Kingdom
Publication History
Published: 14 February 2020
Author Tags
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 01 Jan 2025