Abstract
This preliminary research attempts to address the complexities in classifying the unpredictable textual content of financial reports. The documented experiment extracts a vector of named entities by implementing a hybrid system; a machine learning and logic driven rules engine on an entity per entity basis. We find that recursive pattern matching and manipulation of selected entity classes significantly yields better results for selected named entity types over a standalone Maximum Entropy classifier. We conclude that adopting a hybrid ensemble to store term/key values natively for further lexical analysis is more effective than either approach. We discuss our findings and future research in this promising area.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
The section of a financial statement where management figures discuss numerous aspects of the companys financial position; past, present and future.
References
Cao, M., Chychyla, R., Stewart, T.: Big data analytics in financial statement audits. Account. Horiz. (2015)
Chiticariu, L., Li, Y., Reiss, F.R.: Rule-based information extraction is dead! Long live rule-based information extraction systems! In: EMNLP, pp. 827–832 (2013)
Columbus, C., Viveka, M.T., Murugan, M.N.S.V.: Classifier Based Text Mining Approaches for Data Mining Applications (2015)
Kearney, C., Liu, S.: Textual sentiment in finance: a survey of methods and models. Int. Rev. Financ. Anal. 33, 171–185 (2014)
Gupta, S., Manning, C.D.: Spied: Stanford Pattern-based Information Extraction and Diagnostics. Idibon, Sponsor (2014)
Leong, C.H., Tou, N.H.: Named entity recognition with a maximum entropy approach. In: Proceedings of the 7th Conference on Natural Language Learning at HLT-NAACL, Edmonton, Canada, vol. 4, pp. 160–163 (2003)
Li, X., Xie, H., Chen, L., Wang, J., Deng, X.: News impact on stock price return via sentiment analysis. Knowl.-Based Syst. 69, 14–23 (2014)
Malik, H.H., Bhardwaj, V.S., Fiorletta, H.: Accurate information extraction for quantitative financial events. In: Proceedings of the 20th ACM International Conference on Information and Knowledge Management, pp. 2497–2500. ACM (2011)
Suganthan, G.C.P., Sun, C., Gayatri, K.K., Zhang, H., Yang, F., Rampalli, N., Doan, A.: Why Big Data Industrial Systems Need Rules and What We Can Do About It (2015)
Vasarhelyi, M.A., Kogan, A., Tuttle, B.: Big data in accounting: an overview. Account. Horiz. (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Hampton, P.J., Wang, H., Blackburn, W. (2015). A Hybrid Ensemble for Classifying and Repurposing Financial Entities. In: Bramer, M., Petridis, M. (eds) Research and Development in Intelligent Systems XXXII. SGAI 2015. Springer, Cham. https://doi.org/10.1007/978-3-319-25032-8_15
Download citation
DOI: https://doi.org/10.1007/978-3-319-25032-8_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-25030-4
Online ISBN: 978-3-319-25032-8
eBook Packages: Computer ScienceComputer Science (R0)