臺灣博碩士論文加值系統

本論文使用深度學習演算法，處理下市公司預測之問題。我們搜集一定時間區間內的下市及未下市公司的股票收益當作輸入訊號，並透過兩種屬於深度架構下的深度信念網路以及卷積神經網路來訓練模型，用以預測下一年這些公司將會下市與否。由實驗結果可以得知，本論文提出之方法的預測準確度優於傳統的機器學習演算法。

This thesis provides a new perspective on the corporate delisting prediction problem using deep learning algorithms. By taking the advantages of deep learning, the
representable factors of input data will no longer need to be explicitly extracted, but can be implicitly learned by the deep learning algorithms. We consider the stock returns of both delisting and listing companies as input signals and adopt two of the deep learning architectures, Deep Belief Networks (DBN) and Convolutional Neural Networks (CNN), to train the prediction models. The experimental results show that the proposed approach outperforms traditional machine learning algorithms.

致謝 Ⅰ

中文摘要 Ⅱ

Abstract Ⅲ

1 Introduction 1

2 Related Work 3
2.1 Classical Statistical Models.................... 3
2.1.1 Altman’s Z-Score.......................... 3
2.1.2 Ohlson’s O-Score.......................... 4
2.2 Market-Based Models............................. 5
2.3 Machine Learning Models......................... 5
2.3.1 Logistic Regression....................... 6
2.3.2 Neural Networks (NN)...................... 6
2.3.3 Support Vector Machine (SVM).............. 7

3 Methodology 10
3.1 Stock Return Calculation........................10
3.2 Problem Formulation.............................10
3.3 Deep Belief Network (DBN).......................11
3.3.1 Restricted Boltzmann Machines (RBM).......11
3.3.2 Deep Belief Network (DBN).................12
3.4 Convolutional Neural Network (CNN)..............13

4 Experimental Results 15
4.1 Experimental Settings...........................15
4.1.1 Dataset...................................15
4.1.2 Data Preprocessing........................16
4.1.3 Experimental Settings.....................17
4.2 Experimental Results............................20

5 Conclusions and Future Work 28

Bibliography 29

[1] D. H. Ackley, G. E. Hinton, and T. J. Sejnowski. A learning algorithm for boltzmann machines. Cognitive Science, 9(1):147–169, 1985.
[2] E. I. Altman. Financial ratios, discriminant analysis and the prediction of corporate bankruptcy. The Journal of Finance, 23(4):589–609, 1968.
[3] A. F. Atiya. Bankruptcy prediction for credit risk using neural networks: A survey and new results. Transactions on Neural Networks, 12(4):929–935, 2001.
[4] S. T. Bharath and T. Shumway. Forecasting default with the merton distance to default model. Review of Financial Studies, 21(3):1339–1369, 2008.
[5] C. M. Bishop. Pattern Recognition and Machine Learning, volume 1. Springer New York, 2006.
[6] F. Black and M. Scholes. The pricing of options and corporate liabilities. The Journal of Political Economy, 81(3):637–654, 1973.
[7] Y.-L. Boureau, S. Chopra, Y. LeCun, and M. Ranzato. A unified energy-based framework for unsupervised learning. In Proceeding of International Conference on Artificial Intelligence and Statistics, pages 371–379, 2007.
[8] C.-C. Chang and C.-J. Lin. Libsvm: A library for support vector machines. Transactions on Intelligent Systems and Technology, 2(3):27, 2011.
[9] R. Collobert and J. Weston. A unified architecture for natural language processing: Deep neural networks with multitask learning. In Proceedings of International
conference on Machine Learning, pages 160–167, 2008.
[10] G. Dahl, A.-r. Mohamed, G. E. Hinton, et al. Phone recognition with the meancovariance restricted boltzmann machine. In Proceedings of Advances in Neural Information Processing Systems, pages 469–477, 2010.
[11] G. E. Dahl, D. Yu, L. Deng, and A. Acero. Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition. Transactions on Audio, Speech, and Language Processing, 20(1):30–42, 2012.
[12] D. Duffie, A. Eckner, G. Horel, and L. Saita. Frailty correlated default. The Journal of Finance, 64(5):2089–2123, 2009.
[13] D. Duffie, L. Saita, and K. Wang. Multi-period corporate default prediction with stochastic covariates. Journal of Financial Economics, 83(3):635–665, 2007.
[14] A. Fan and M. Palaniswami. A new approach to corporate loan default prediction from financial statements. In Proceedings of Computational Finance/Forecasting Financial Markets Conference, 2000.
[15] G. Hinton. A practical guide to training restricted boltzmann machines. Momentum, 9(1):926, 2010.
[16] G. Hinton, L. Deng, D. Yu, G. E. Dahl, A.-r. Mohamed, N. Jaitly, A. Senior, V. Vanhoucke, P. Nguyen, T. N. Sainath, et al. Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups. Signal Processing Magazine, 29(6):82–97, 2012.
[17] G. E. Hinton. Training products of experts by minimizing contrastive divergence. Neural Computation, 14(8):1771–1800, 2002.
[18] G. E. Hinton and R. R. Salakhutdinov. Reducing the dimensionality of data with neural networks. Science, 313(5786):504–507, 2006.
[19] A. Krizhevsky, I. Sutskever, and G. E. Hinton. Imagenet classification with deep convolutional neural networks. In Proceeding of Advances in Neural Information
Processing Systems, pages 1097–1105, 2012.
[20] Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner. Gradient-based learning applied to document recognition. In Intelligent Signal Processing, pages 306–351, 2001.
[21] H. Lee, R. Grosse, R. Ranganath, and A. Y. Ng. Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations. In Proceedings of International Conference on Machine Learning, pages 609–616, 2009.
[22] H. Lee, P. Pham, Y. Largman, and A. Y. Ng. Unsupervised feature learning for audio classification using convolutional deep belief networks. In Proceedings of Advances in Neural Information Processing Systems, pages 1096–1104, 2009.
[23] R. C. Merton. On the pricing of corporate debt: The risk structure of interest rates. The Journal of Finance, 29(2):449–470, 1974.
[24] J. H. Min and Y.-C. Lee. Bankruptcy prediction using support vector machine with optimal choice of kernel function parameters. Expert Systems with Applications,
28(4):603–614, 2005.
[25] A.-r. Mohamed, G. E. Dahl, and G. Hinton. Acoustic modeling using deep belief networks. Transactions on Audio, Speech, and Language Processing, 20(1):14–22,
2012.
[26] A.-r. Mohamed, T. N. Sainath, G. Dahl, B. Ramabhadran, G. E. Hinton, and M. A. Picheny. Deep belief networks using discriminative features for phone recognition. In Proceedings of International Conference on Acoustics, Speech and Signal Processing, pages 5060–5063, 2011.
[27] M. D. Odom and R. Sharda. A neural network model for bankruptcy prediction. In International Joint Conference on Neural Networks, pages 163–168, 1990.
[28] J. A. Ohlson. Financial ratios and the probabilistic prediction of bankruptcy. Journal of Accounting Research, 18(1):109–131, 1980.
[29] R. Salakhutdinov, A. Mnih, and G. Hinton. Restricted boltzmann machines for collaborative filtering. In Proceedings of International Conference on Machine Learning, pages 791–798, 2007.
[30] K.-S. Shin, T. S. Lee, and H.-j. Kim. An application of support vector machines in bankruptcy prediction model. Expert Systems with Applications, 28(1):127–135,
2005.
[31] T. Tieleman. Training restricted boltzmann machines using approximations to the likelihood gradient. In Proceedings of International Conference on Machine Learning, pages 1064–1071, 2008.
[32] R. S. Tsay. Analysis of financial time series, volume 543. Wiley Interscience, 2005.
[33] Wikipedia. Support vector machine — Wikipedia, the free encyclopedia. [Online; accessed 2-October-2015].