Abstract
We consider the task of predicting the class of commentaries associated with financial discrepancies between actual and estimated sales data. Such analysis of the financial data is helpful in meeting targets and assessing the overall performance of the company. While generating a commentary and its associated class is the task of an analyst, these manual operations might be erroneous and as a result, might lead to a diminished performance for the employed prediction model due to wrong class labels. Accordingly, we propose using topic modelling, namely Latent Dirichlet Allocation (LDA), for automated extraction of the classes of the commentaries. In addition, we use feature selection strategies to improve the accuracy of the prediction models. Our analysis with various time series classification methods points to improved performance due to LDA and feature selection.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Bagnall, A., Lines, J., Bostrom, A., Large, J., Keogh, E.: The great time series classification bake off: a review and experimental evaluation of recent algorithmic advances. Data Min. Knowl. Disc. 31(3), 606–660 (2016). https://doi.org/10.1007/s10618-016-0483-9
Blei, D., Ng, A., Jordan, M.: Latent dirichlet allocation. JMLR 3, 993–1022 (2003)
Deerwester, S., Dumais, S.T., Furnas, G.W., Landauer, T.K., Harshman, R.: Indexing by latent semantic analysis. J. Am. Soc. Inf. Sci. 41(6), 391–407 (1990)
El Mokhtari, K., Higdon, B., Başar, A.: Interpreting financial time series with SHAP values. In: Proceedings of the 29th Annual International Conference on Computer Science and Software Engineering, pp. 166–172 (2019)
El Mokhtari, K., Maidens, J., Bener, A.: Predicting commentaries on a financial report with recurrent neural networks. In: Meurs, M.-J., Rudzicz, F. (eds.) Canadian AI 2019. LNCS (LNAI), vol. 11489, pp. 531–542. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-18305-9_56
Peachey Higdon, B., El Mokhtari, K., Başar, A.: Time-series-based classification of financial forecasting discrepancies. In: Bramer, M., Petridis, M. (eds.) SGAI 2019. LNCS (LNAI), vol. 11927, pp. 474–479. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-34885-4_39
Hofmann, T.: Probabilistic latent semantic indexing. In: Proceedings of the 22nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 50–57 (1999)
Asadi Kakhki, S.S., Kavaklioglu, C., Bener, A.: Topic detection and document similarity on financial news. In: Bagheri, E., Cheung, J.C.K. (eds.) Canadian AI 2018. LNCS (LNAI), vol. 10832, pp. 322–328. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-89656-4_34
Lee, S., Baker, J., Song, J., Wetherbe, J.C.: An empirical comparison of four text mining methods. In: 2010 43rd Hawaii International Conference on System Sciences, pp. 1–10, January 2010. https://doi.org/10.1109/HICSS.2010.48
Liu, Y., Huang, X., An, A., Yu, X.: ARSA: a sentiment-aware model for predicting sales performance using blogs. In: Proceedings of the 30th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 607–614 (2007)
Miao, J., Huang, J.X., Zhao, J.: TopPRF: a probabilistic framework for integrating topic space into pseudo relevance feedback. ACM TOIS 34(4), 1–36 (2016)
Park, S., Choi, D., Kim, M., Cha, W., Kim, C., Moon, I.C.: Identifying prescription patterns with a topic model of diseases and medications. J. Biomed. Inform. 75, 35–47 (2017)
Acknowledgement
This work is supported by Smart Computing For Innovation (SOSCIP) consortium, Toronto, Canada.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
El Mokhtari, K., Cevik, M., Başar, A. (2020). Using Topic Modelling to Improve Prediction of Financial Report Commentary Classes. In: Goutte, C., Zhu, X. (eds) Advances in Artificial Intelligence. Canadian AI 2020. Lecture Notes in Computer Science(), vol 12109. Springer, Cham. https://doi.org/10.1007/978-3-030-47358-7_19
Download citation
DOI: https://doi.org/10.1007/978-3-030-47358-7_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-47357-0
Online ISBN: 978-3-030-47358-7
eBook Packages: Computer ScienceComputer Science (R0)