SuperDeConFuse: A supervised deep convolutional transform based fusion framework for financial trading systems. (1st May 2021)

• Record Type: Journal Article
• Authors: Gupta, Pooja; Majumdar, Angshul; Chouzenoux, Emilie; Chierchia, Giovanni
• Is Part Of: Expert systems with applications. Volume 169(2021)
• Publication Date: 2021-05-01
• Subjects: Information fusion -- Deep learning -- Convolution -- Transform learning -- Stock trading; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2020.114206
• Languages: English
• ISSNs: 0957-4174

Abstract

Abstract: This work proposes a supervised multi-channel time-series learning framework for financial stock trading. Although many deep learning models have recently been proposed in this domain, most of them treat the stock trading time-series data as 2-D image data, whereas its true nature is 1-D time-series data. Since the stock trading systems are multi-channel data, many existing techniques treating them as 1-D time-series data are not suggestive of any technique to effectively fusion the information carried by the multiple channels. To contribute towards both of these shortcomings, we propose an end-to-end supervised learning framework inspired by the previously established (unsupervised) convolution transform learning framework. Our approach consists of processing the data channels through separate 1-D convolution layers, then fusing the outputs with a series of fully-connected layers, and finally applying a softmax classification layer. The peculiarity of our framework, that we call SuperDeConFuse (SDCF), is that we remove the nonlinear activation located between the multi-channel convolution layers and the fully-connected layers, as well as the one located between the latter and the output layer. We compensate for this removal by introducing a suitable regularization on the aforementioned layer outputs and filters during the training phase. Specifically, we apply a logarithm determinant regularization on the layer filters to break symmetry and force diversity in the learnt transforms, whereas we enforce the non-negativity constraint on the layer outputs to mitigate the issue of dead neurons. This results in the effective learning of a richer set of features and filters with respect to a standard convolutional neural network. Numerical experiments confirm that the proposed model yields considerably better results than state-of-the-art deep learning techniques for the real-world problem of stock trading. Highlights: The work proposes a novel supervised learning framework, for fusion of multi-channel information. It is based on the recently established Convolutional Transform Learning technique. The practical goal is to perform classification tasks on stock trading financial data. The model keeps up with the univariate and sequential nature of the time-series financial data. It improves over the state-of-the-art methods.