Research PaperNo Access

Company2Vec — German Company Embeddings Based on Corporate Websites

Chair of Information Systems, Humboldt University of Berlin, Berlin, Germany

https://doi.org/10.1142/S0219622023500694Cited by:3 (Source: Crossref)

Abstract

With Company2Vec, the paper proposes a novel application in representation learning. The model analyzes business activities from unstructured company website data using Word2Vec and dimensionality reduction. Company2Vec maintains semantic language structures and thus creates efficient company embeddings in fine-granular industries. These semantic embeddings can be used for various applications in banking.

Direct relations between companies and words allow semantic business analytics (e.g., top-n words for a company). Furthermore, industry prediction is presented as a supervised learning application and evaluation method. The vectorized structure of the embeddings allows measuring companies’ similarities with the cosine distance. Company2Vec hence offers a more fine-grained comparison of companies than the standard industry labels (NACE). This property is relevant for unsupervised learning tasks, such as clustering. An alternative industry segmentation is shown with k-means clustering on the company embeddings. Finally, this paper proposes three algorithms for (1) firm-centric, (2) industry-centric and (3) portfolio-centric peer-firm identification.

Keywords:

References

1. T. Mikolov, K. Chen, G. Corrado and J. Dean , Efficient estimation of word representations in vector space, 1st Int. Conf. Learning Representations, ICLR 2013, May 2–4 2013, Scottsdale, Arizona, http://arXiv.org/abs/1301.3781. Google Scholar
2. Q. Le and T. Mikolov , Distributed representations of sentences and documents, in Proc. 31st Int. Conf. Machine Learning, ICML’14 (PMLR, 2014), pp. 1188–1196. Google Scholar
3. S. Gabel, D. Guhl and D. Klapper , P2v-map: Mapping market structures for large retail assortments, Journal of Marketing Research 56(4) (2019) 557–580, https://doi.org/10.1177/0022243719833631. Crossref, Web of Science, Google Scholar
4. A. Budhrani, A. Patel and S. Ribadiya , Music2vec: Music genre classification and recommendation system, 2020 4th Int. Conf. Electronics, Communication and Aerospace Technology (ICECA), 5-7 November 2020, Coimbatore, India, pp. 1406–1411. Google Scholar
5. H. Zhang and G. Kou , Role-based multiplex network embedding, in Proc. 39th Int. Conf. Machine Learning, eds. K. Chaudhuri, S. Jegelka, L. Song, C. Szepesvari, G. Niu and S. Sabato , (PMLR, 2022), pp. 26265–26280, https://proceedings.mlr.press/v162/zhang22m.html. Google Scholar
6. G. Kou, Y. Xu, Y. Peng, F. Shen, Y. Chen, K. Chang and S. Kou , Bankruptcy prediction for smes using transactional data and two-stage multiobjective feature selection, Decision Support Systems 140 (2021) 113429, https://www.sciencedirect.com/science/article/pii/S0167923620301846. Crossref, Web of Science, Google Scholar
7. Statistisches Bundesamt, Klassifikation der Wirtschaftszweige (2008), https://www.destatis.de/DE/Methoden/Klassifikationen/Gueter-Wirtschaftsklas sifikationen/Downloads/klassifikation-wz-2008-3100100089004-aktuell.pdf. Google Scholar
8. G. A. Keskin , A novel perspective to sustainable supplier performance evaluation problem: A case study based on determining the optimum number of clusters, International Journal of Information Technology & Decision Making 21(04) (2022) 1349–1379, https://doi.org/10.1142/S0219622022500195. Link, Web of Science, Google Scholar
9. Z. Yi, T. Xiao, K. Ijeoma, R. Cheran, Y. Baweja and P. Nelson, Stock2vec: An embedding to improve predictive models for companies (2022), arXiV:2201.11290. Google Scholar
10. J. M. Pierre, On the automated classification of web sites (2001), https://arXiv.org/abs/cs/0102002. Google Scholar
11. G. Berardi, A. Esuli, T. Fagni and F. Sebastiani , Classifying websites by industry sector: A study in feature design, in Proc. 30th Annual ACM Symposium on Applied Computing, SAC’15 (New York, USA, 2015), pp. 1053–1059, https://doi.org/10.1145/2695664.2695722. Crossref, Google Scholar
12. A. Bernstein, S. Clearwater and F. Provost , The relational vector-space model and industry classification, in Proc. IJCAI Workshop on Statistical Models from Relational Data (2003), pp. 8–18. Google Scholar
13. T. Kee , Peer firm identification using word embeddings, 2019 IEEE Int. Conf. Big Data (Big Data) (2019), pp. 5536–5543. Crossref, Google Scholar
14. F. Fang, K. Dutta, and A. Datta , Lda-based industry classification, Thirty Fourth Int. Con. on Information Systems (Milan, Italy, 2013), pp. 1–10. Google Scholar
15. A. Fodor, R. D. Jorgensen and J. D. Stowe , Forming Stock Groups with a Cluster Analysis of Common Size Statements, in Southwestern Finance Association Annual Conference (2015), pp. 1–36. Google Scholar
16. P. Gkotsis, E. Pugliese and A. Vezzani , A technology-based classification of firms: Can we learn something looking beyond industry classifications? Entropy 20(11) (2018), https://www.mdpi.com/1099-4300/20/11/887. Crossref, Google Scholar
17. S. Husmann, A. Shivarova and R. Steinert , Company classification using machine learning, Expert Systems with Applications 195 (2022) 116598, https://www.sciencedirect.com/science/article/pii/S0957417422000914. Crossref, Web of Science, Google Scholar
18. T. Li, G. Kou, Y. Peng and P. S. Yu , An integrated cluster detection, optimization, and interpretation approach for financial data, IEEE Transactions on Cybernetics 52(12) (2022) 13848–13861. Crossref, Web of Science, Google Scholar
19. C. M. Lee, P. Ma and C. C. Wang , Search-based peer firms: Aggregating investor perceptions through internet co-searches, Journal of Financial Economics 116(2) (2015) 410–431, https://www.sciencedirect.com/science/article/pii/S0304405X15000197. Crossref, Web of Science, Google Scholar
20. M. Kaustia and V. Rantala , Common analysts: Method for defining peer firms, Journal of Financial and Quantitative Analysis 56(5) (2021) 1505–1536. Crossref, Web of Science, Google Scholar
21. S. Rönnqvist and P. Sarlin , Bank networks from text: Interrelations, centrality and determinants, Quantitative Finance 15(10) (2015) 1619–1635, https://doi.org/10.1080/14697688.2015.1071076. Crossref, Web of Science, Google Scholar
22. G. Hoberg and G. Phillips , Text-based network industries and endogenous product differentiation, Journal of Political Economy 124(5) (2016) 1423–1465, https://EconPapers.repec.org/RePEc:ucp:jpolec:doi:10.1086/688176. Crossref, Web of Science, Google Scholar
23. T. Ito, J. C. Collados, H. Sakaji and S. Schockaert , Learning company embeddings from annual reports for fine-grained industry characterization, in Proc. Second Workshop on Financial Technology and Natural Language Processing (Kyoto, Japan, 2020), pp. 27–33, https://aclanthology.org/2020.finnlp-1.5 Google Scholar
24. A. Müller, Analyse von Wort-Vektoren deutscher Textkorpora (2015), https://devmount.github.io/GermanWordEmbeddings. Google Scholar
25. M. Fares, A. Kutuzov, S. Oepen and E. Velldal , Word vectors, reuse, and replicability: Towards a community repository of large-text resources, in Proc. 21st Nordic Conf. Computational Linguistics (Gothenburg, Sweden, 2017), pp. 271–276, https://aclanthology.org/W17-0237. Google Scholar
26. I. Yamada, A. Asai, H. Shindo, H. Takeda and Y. Takefuji, Wikipedia2vec: An optimized tool for learning embeddings of words and entities from wikipedia (2018), http://arXiv.org/abs/1812.06280. Google Scholar
27. D. Angelov, Top2vec: Distributed representations of topics (2020), https://arXiv.org/abs/2008.09470. Google Scholar
28. D. M. Blei, A. Y. Ng and M. I. Jordan , Latent dirichlet allocation, Journal of Machine Learning Research 3 (2003) 993–1022, http://portal.acm.org/citation.cfm?id=944937. Web of Science, Google Scholar
29. L. Finkelstein, E. Gabrilovich, Y. Matias, E. Rivlin, Z. Solan, G. Wolfman and E. Ruppin , Placing search in context: The concept revisited, in Proc. 10th Int. Conf. World Wide Web (ACM, 2001), pp. 406–414. Crossref, Google Scholar
30. F. Hill, R. Reichart and A. Korhonen, Simlex-999: Evaluating semantic models with (genuine) similarity estimation (2014), http://arXiv.org/abs/1408.3456. Google Scholar
31. N. V. Chawla, K. W. Bowyer, L. O. Hall and W. P. Kegelmeyer , SMOTE: Synthetic minority over-sampling technique, Journal of Artificial Intelligence Research 16 (2002) 321–357, http://dx.doi.org/10.1613/jair.953. Crossref, Web of Science, Google Scholar
32. L. van der Maaten and G. Hinton , Visualizing data using t-SNE, Journal of Machine Learning Research 9 (2008) 2579–2605, http://www.jmlr.org/papers/v9/vandermaaten08a.html. Web of Science, Google Scholar
33. J. Devlin, M.-W. Chang, K. Lee and K. Toutanova , BERT: Pre-training of deep bidirectional transformers for language understanding, in Proc. 2019 Conf. North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Minneapolis, Minnesota, 2019), pp. 4171–4186, https://aclanthology.org/N19-1423. Google Scholar
34. T. Mikolov, I. Sutskever, K. Chen, G. Corrado and J. Dean, Distributed representations of words and phrases and their compositionality (2013), http://arXiv.org/abs/1310.4546. Google Scholar
35. A. Singhal , Modern information retrieval: A brief overview, IEEE Data Engineering Bulletin 24 (2001) 35–43. Google Scholar
36. P. Covington, J. Adams and E. Sargin , Deep neural networks for YouTube recommendations, in Proc. 10th ACM Conf. Recommender Systems, RecSys’16 (New York, USA, 2016), pp. 191–198, https://doi.org/10.1145/2959100.2959190. Crossref, Google Scholar
37. Y. Xu, T. Lv, L. Cui, G. Wang, Y. Lu, D. Florêncio, C. Zhang and F. Wei, LayoutXLM: Multimodal pre-training for multilingual visually-rich document understanding (2021), https://arXiv.org/abs/2104.08836. Google Scholar
38. OpenAI, GPT-4 Technical Report (2023), https://arXiv.org/abs/ 2303.08774. Google Scholar