Please use this identifier to cite or link to this item:
https://ah.lib.nccu.edu.tw/handle/140.119/141068| 題名: | 基於自然語言分析建構預測企業信用評等變動之模型 Construction of Corporate Credit Rating Prediction Model Based on Natural Language Analysis |
作者: | 陳明勝 Chen, Ming-Sheng |
貢獻者: | 江彌修<br>趙世偉 Chiang, Mi-Hsiu<br>Chao, Shih-Wei 陳明勝 Chen, Ming-Sheng |
關鍵詞: | 自然語言分析 神經網路 領域遷移 企業信用預警 Natural Language Analysis Neural Network Domain Adaption Corporate Credit Prediction |
日期: | 2022 | 上傳時間: | 1-Aug-2022 | 摘要: | 為改進過去語言分析模型無法辨認語言一字多義以及訓練域與預測域不一致之問題，本研究嘗試以BERT(Bidirectional Encoder Representations from Transformers)模型針對金融領域文本進行領域遷移(Domain Adaption)，比較有無經過遷移對模型效能之改進，接著以遷移過之模型分析RavenPack資料庫內所含的美國企業相關新聞，並以此建構信用評等變動預警模型。\n\n本研究實證結果顯示，經過遷移之模型預測財金文本情緒的預測準確率比未經遷移之模型高出30.47%，且領域遷移後辨認的新聞情緒提升對未來企業信用評等變動的預測。另外，本研究建構四個隨機森林模型，用以證明企業金融財務面的媒體情緒隱含對企業未來評級可能變動的有效資訊。 To improve the inability of the language analysis model to recognize the polysemy of the language and the inconsistency between the training domain and the prediction domain, this study uses the BERT (Bidirectional Encoder Representations from Transformers) model to perform Domain Adaption for the financial corpus. The adaption improves the performance of the model, and we further use the adapted model to analyze the news related to US companies contained in the RavenPack database and construct an early warning model for credit rating changes.\n\nThe empirical results show that the prediction accuracy of the adapted model in predicting the sentiment of financial texts is 30.47% higher than that of the non-adapted one, which shows that adaption learning indeed improves the prediction of the corporate credit rating changes. Also, we developed four different random forest models to prove that the media sentiment on the company`s financial news contains effective information on the possible changes in the company`s future rating. |
參考文獻: | Altman, E. I. (1968). Financial ratios, discriminant analysis and the prediction of corporate\nbankruptcy. The Journal of Finance, 23(4):589–609.\nAraci, D. (2019). Finbert: Financial sentiment analysis with pre-trained language models.\narXiv preprint arXiv:1908.10063.\nBlei, D. M., Ng, A. Y., and Jordan, M. I. (2003). Latent dirichlet allocation. Journal of\nMachine Learning Research, 3(Jan):993–1022.\nCollin-Dufresn, P., Goldstein, R. S., and Martin, J. S. (2001). The determinants of credit\nspread changes. The Journal of Finance, 56(6):2177–2207.\nDa, Z., Engelberg, J., and Gao, P. (2015). The sum of all fears investor sentiment and asset\nprices. The Review of Financial Studies, 28(1):1–32.\nDevlin, J., Chang, M.-W., Lee, K., and Toutanova, K. (2018). Bert: Pre-training\nof deep bidirectional transformers for language understanding. arXiv preprint\narXiv:1810.04805.\nDyer, T., Lang, M., and Stice-Lawrence, L. (2017). The evolution of 10-k textual disclosure: Evidence from latent dirichlet allocation. Journal of Accounting and Economics,\n64(2-3):221–245.\nEricsson, J., Jacobs, K., and Oviedo, R. (2009). The determinants of credit default swap\npremia. Journal of Financial and Quantitative Analysis, 44(1):109–132.\nFama, E. F. (1960). Efficient market hypothesis. Diss. PhD Thesis, Ph. D. dissertation.\nGalil, K. and Soffer, G. (2011). Good news, bad news and rating announcements: An\nempirical investigation. Journal of Banking & Finance, 35(11):3101–3119.\nHajek, P. and Michalak, K. (2013). Feature selection in corporate credit rating prediction.\nKnowledge-Based Systems, 51:72–84.\nHuang, A. H., Lehavy, R., Zang, A. Y., and Zheng, R. (2018). Analyst information discovery and interpretation roles: A topic modeling approach. Management Science,\n64(6):2833–2855.\nHull, J., Predescu, M., and White, A. (2004). The relationship between credit default swap\nspreads, bond yields, and credit rating announcements. Journal of Banking & Finance,\n28(11):2789–2811.\nHutto, C. and Gilbert, E. (2014). Vader: A parsimonious rule-based model for sentiment\nanalysis of social media text. In Proceedings of the International AAAI Conference on\nWeb and Social Media, volume 8, pages 216–225.\nJarrow, R. A. and Turnbull, S. M. (1995). Pricing derivatives on financial securities subject\nto credit risk. The Journal of Finance, 50(1):53–85.\nLan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., and Soricut, R. (2019). Albert: A lite bert for self-supervised learning of language representations. arXiv preprint\narXiv:1909.11942.\nLawrence, A. (2013). Individual investors and financial disclosure. Journal of Accounting\nand Economics, 56(1):130–147.\nLee, Y.-C. (2007). Application of support vector machines to corporate credit rating prediction. Expert Systems with Applications, 33(1):67–74.\nLi, F. (2008). Annual report readability, current earnings, and earnings persistence. Journal of Accounting and Economics, 45(2-3):221–247.\nLi, X., Xie, H., Chen, L., Wang, J., and Deng, X. (2014). News impact on stock price\nreturn via sentiment analysis. Knowledge-Based Systems, 69:14–23.\nLiberti, J. M. and Petersen, M. A. (2019). Information: Hard and soft. Review of Corporate\nFinance Studies, 8(1):1–41.\nLoughran, T. and McDonald, B. (2011). When is a liability not a liability? textual analysis,\ndictionaries, and 10-ks. The Journal of Finance, 66(1):35–65.\nLoughran, T. and McDonald, B. (2014). Measuring readability in financial disclosures.\nthe Journal of Finance, 69(4):1643–1671.\nLoughran, T. and McDonald, B. (2016). Textual analysis in accounting and finance: A\nsurvey. Journal of Accounting Research, 54(4):1187–1230.\nLu, H.-M., Tsai, F.-T., Chen, H., Hung, M.-W., and Li, S.-H. (2012). Credit rating change\nmodeling using news and financial ratios. ACM Transactions on Management Information Systems (TMIS), 3(3):1–30.\nLundberg, S. M. and Lee, S.-I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems, 30.\nMayew, W. J. and Venkatachalam, M. (2012). The power of voice: Managerial affective\nstates and future firm performance. The Journal of Finance, 67(1):1–43.\nMerton, R. C. (1973). Theory of rational option pricing. The Bell Journal of Economics\nand Management Science, pages 141–183.\nMerton, R. C. (1974). On the pricing of corporate debt: The risk structure of interest rates.\nThe Journal of Finance, 29(2):449–470.\nMiller, B. P. (2010). The effects of reporting complexity on small and large investor\ntrading. The Accounting Review, 85(6):2107–2143.\nNorden, L. (2017). Information in cds spreads. Journal of Banking & Finance, 75:118–\n135.\nNorden, L. and Weber, M. (2004). Informational efficiency of credit default swap and\nstock markets: The impact of credit rating announcements. Journal of Banking & Finance, 28(11):2813–2843.\nOrsenigo, C. and Vercellis, C. (2013). Linear versus nonlinear dimensionality reduction\nfor banks’credit rating prediction. Knowledge-Based Systems, 47:14–22.\nPedrosa, M. (1998). Systematic risk in corporate bond credit spreads. Journal of Fixed\nIncome, 8(3):7–26.\nRaffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., Liu,\nP. J., et al. (2020). Exploring the limits of transfer learning with a unified text-to-text\ntransformer. J. Mach. Learn. Res., 21(140):1–67.\nShapiro, A. H., Sudhof, M., and Wilson, D. J. (2020). Measuring news sentiment. Journal\nof Econometrics.\nSmales, L. A. (2016). News sentiment and bank credit risk. Journal of Empirical Finance,\n38:37–61.\nTetlock, P. C. (2007). Giving content to investor sentiment: The role of media in the stock\nmarket. The Journal of Finance, 62(3):1139–1168.\nTetlock, P. C., Saar-Tsechansky, M., and Macskassy, S. (2008). More than words: Quantifying language to measure firms’ fundamentals. The journal of finance, 63(3):1437–\n1467.\nVaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł.,\nand Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information\nProcessing Systems, 30.\nYang, Z., Dai, Z., Yang, Y., Carbonell, J., Salakhutdinov, R. R., and Le, Q. V. (2019).\nXlnet: Generalized autoregressive pretraining for language understanding. Advances\nin Neural Information Processing Systems, 32. | 描述: | 碩士 國立政治大學 金融學系 109352029 |
資料來源: | http://thesis.lib.nccu.edu.tw/record/#G0109352029 | 資料類型: | thesis |
| Appears in Collections: | 學位論文 |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 202901.pdf | 2.38 MB | Adobe PDF2 | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.