Abstract
The futures market's forecasts are significant to investors and policymakers, where the application of deep learning approaches to finance has received a great deal of attention. In this study, we propose a multivariate financial time-series forecasting method. Our model addresses the long- and short-term features, multimodal and non-stationarity nature of multivariate time-series by incorporating the improved deep neural networks and certified noise injection. Specifically, multimodal variational autoencoder is used to extract deep high-level features of multivariate time-series, Long- and Short- Term recurrent neural network is applied for multivariate time-series forecasting, and certified noise injection mechanism, inspired by differential privacy, is proposed to improve the robustness and accuracy of prediction. Extensive empirical results on real-world agricultural commodity futures price time series and relevant external data demonstrate that our model achieves better performance over that of several state-of-the-art baseline methods.
Highlights
Considering the significance of the futures market in the financial field, forecasting futures price movements is critical to investors and policymakers
To address the challenges mentioned in the introduction, our prediction model differential privacy (DP)-MAELS without robustness enhanced strategies (MAELS) is composed of three components: (C1) multimodal-variational autoencoder (VAE) for addressing the local dependency patterns among multi-dimensional input variables and feature extraction, (C2) LST-prediction for the multivariate time-series prediction, including a recurrent component to discover the short-term patterns in the time dimension, a recurrent-skip component to discover long-term patterns for time series trends (C3) provable noise injection to improve the robustness of prediction against non-stationary nature
DATASETS we conduct an extensive evaluation to validate our DP-MAELS based on the multivariate agricultural commodity futures prices and relevant external data
Summary
Considering the significance of the futures market in the financial field, forecasting futures price movements is critical to investors and policymakers. Such methodologies have several distinct advantages such as non-parametric, self-learning, non-assumption, and noisetolerant [9]. A. AUTOENCODERS AND VARIATIONS Autoencoders (AEs) are common deep models in unsupervised learning [11]. AUTOENCODERS AND VARIATIONS Autoencoders (AEs) are common deep models in unsupervised learning [11] It aims to represent high-dimensional data through the low-dimensional latent layer, a.k.a. Bottleneck vector or code. An encoder E, parameterized by qφ(z|x), is trained to convert high-dimensional data x into the latent representation bottleneck vector z in latent space that follows a specific Gaussian distribution p(z) ∼ N (0, 1). The decoder pθ (x|z) is trained to reconstruct the latent vector z to x.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
