×

Learning uncertainty in market trend forecast using Bayesian neural networks. (English) Zbl 1447.91170

Bucciarelli, Edgardo (ed.) et al., Decision economics: complexity of decisions and decisions for complexity. Papers based on the presentations at the international conference on decision economics, DECON 2019, Ávila, Spain, June 26–28, 2019. Cham: Springer. Adv. Intell. Syst. Comput. 1009, 210-218 (2020).
Summary: Forecasting financial market trends is challenging. Predicting financial market trends always involves uncertainty because the economy is a complex system with a wide variety of interactions. Thus, to consider uncertainty, trends must be estimated stochastically. Conventional machine learning and deep learning methods cannot learn prediction uncertainty, and predicted “probabilities” calculated using such methods are unreliable. Bayesian neural networks (BNN) have been studied relative to their ability to consider uncertainty. A BNN enables Bayesian inference by considering a prior distribution of parameters in a neural network (NN). We have proposed a Bayesian convolutional neural network (CNN) method to predict short-term stock price trends using stock order data. We used a CNN to learn the series features of the stock order data and a dropout technique is employed to enable Bayesian inference. The proposed Bayesian CNN model trained prediction uncertainty properly, and the predicted probability calculated by the proposed model is more likely to predict the actual market movement than the conventional CNN and logistic regression models. It is expected that using Bayesian CNN will provide more reliable market trend forecasts.
For the entire collection see [Zbl 1444.91005].

MSC:

91G15 Financial markets
62P05 Applications of statistics to actuarial sciences and financial mathematics
62M20 Inference from stochastic processes and prediction
91-08 Computational methods for problems pertaining to game theory, economics, and finance

Software:

Adam; ImageNet; AlexNet
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Blundell, C., Julien, C., Koray, K., Daan, W.: Weight uncertainty in neural networks. In: The 32nd International Conference on Machine Learning, pp. 1613-1622 (2015)
[2] Ericsson, N.R.: Forecast Uncertainty in Economic Modeling. FRB International Finance Discussion Paper 697 (2001)
[3] Dietterich, T.G.: Ensemble methods in machine learning multiple classifier systems, pp. 1-15 (2000)
[4] Kendall, A., Gal, Y.: What uncertainties do we need in Bayesian deep learning for computer vision? In: Advances in Neural Information Processing Systems, pp. 5580-5590 (2017)
[5] Kingma, D., Ba, J.: Adam: a method for stochastic optimization. In: The 3rd International Conference on Learning Representations (2015)
[6] Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097-1105 (2012)
[7] Nassirtoussi, A.K., Aghabozorgi, S., Ying Wah, T., Ngo, D.C.L.: Text mining for market prediction: a systematic review. Expert Syst. Appl. 41, 7653-7670 (2014) · doi:10.1016/j.eswa.2014.06.009
[8] Rasmussen, C.E., Williams, C.K.I.: Gaussian Processes for Machine Learning. The MIT Press, Cambridge (2005) · Zbl 1177.68165 · doi:10.7551/mitpress/3206.001.0001
[9] Silver, N.: The Signal and the Noise: Why So Many Predictions Fail-but Some Don’t. Penguin Books, London (2015)
[10] Vui, C.S., Soon, G.K., On, C.K., Alfred, R., Anthony, P.: A review of stock market prediction with artificial neural network (ANN). In: 2013 IEEE International Conference on Control System, Computing and Engineering (ICCSCE), pp. 477—482 (2013)
[11] Wang, Z., Yan, W., Oates, T.: Time series classification from scratch with deep neural networks: a strong baseline. In: Proceedings of the International Joint Conference on Neural Networks, pp. 1578-1585 (2017)
[12] Williams, C.K.I., Barber, D.: Bayesian classification with Gaussian processes. IEEE Trans. Pattern Anal. Mach. Intell. 20, 1342-1351 (1998) · doi:10.1109/34.735807
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.