Support Tensor Machine for Financial Forecasting

Calvi, Giuseppe G.; Lucic, Vladimir; Mandic, Danilo P.

doi:10.1109/icassp.2019.8683383

Cited by 13 publications

(7 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the given task, we compared the performance of the proposed TT-RNN against: (i) its uncompressed RNN counterpart, (ii) a TT fully-connected neural network (TTNN) [13], and (iii) a Support Tensor Machine (STM) [31]. To evaluate the performance of each model, we considered: (i) the annualized Sharpe ratio of the profits generated in the test-period (defined as √ 252 ur σr , where u r is the average daily returns and σ r is the standard deviation of daily returns), (ii) total returns generated, and (iii) the directional accuracy of the predictions.…”

Section: Resultsmentioning

confidence: 99%

Tensor-Train Recurrent Neural Networks for Interpretable Multi-Way Financial Forecasting

Xu¹,

Calvi²,

Mandic³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Recurrent Neural Networks (RNNs) represent the de facto standard machine learning tool for sequence modelling, owing to their expressive power and memory. However, when dealing with large dimensional data, the corresponding exponential increase in the number of parameters imposes a computational bottleneck. The necessity to equip RNNs with the ability to deal with the curse of dimensionality, such as through the parameter compression ability inherent to tensors, has led to the development of the Tensor-Train RNN (TT-RNN). Despite achieving promising results in many applications, the full potential of the TT-RNN is yet to be explored in the context of interpretable financial modelling, a notoriously challenging task characterized by multi-modal data with low signal-to-noise ratio. To address this issue, we investigate the potential of TT-RNN in the task of financial forecasting of currencies. We show, through the analysis of TT-factors, that the physical meaning underlying tensor decomposition, enables the TT-RNN model to aid the interpretability of results, thus mitigating the notorious "black-box" issue associated with neural networks. Furthermore, simulation results highlight the regularization power of TT decomposition, demonstrating the superior performance of TT-RNN over its uncompressed RNN counterpart and other tensor forecasting methods.

show abstract

Section: Resultsmentioning

confidence: 99%

Tensor-Train Recurrent Neural Networks for Interpretable Multi-Way Financial Forecasting

Xu¹,

Calvi²,

Mandic³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…ML communities should handle the high-order data and tensor can capture the three or higher-order feature rather than unfolding the high-order data into matrix or vector. When the learning data has high-order feature, i.e., Human Recognition Data, Spatiotemporal Dynamics Data, Tensor Regression [9], [10], [11] can project multi-attribute weather data into the forecasting value, and Support Tensor Machine [12], [13], [14] can find the discrete classification value from multi-attribute data. DCNN plays a key role to learn deep feature from plenty of data, and the tensor decomposition can reduce the parameter complexity [31], [32].…”

Section: Related Workmentioning

confidence: 99%

“…In ML communities, tensor applications can be divided into the following three classes: (1)In order to capture the general feature of multi-modal data, muiti-view learning always combines multi-feature into a tensor space [5], [6], [7], [8]. (2) To project the multi-attribute data into a low complexity and low-rank space, the learning weight variable always be constituted tensor data, etc, Tensor Regression [9], [10], [11], Support Tensor Machine [12], [13], [14], and Deep Convolutional Neural Networks (DCNN) in TensorFlow and Pytorch framework [15]; (3) Due to the spatiotemporal dynamics and multi-attribute interaction, the forming data is naturally tensor, e.g, in Recommendation Systems [16], Quality of Service (QoS) [17], Network Flow [18], Cyber-Physical-Social (CPS) [19], or Social Networks [20]. The scale of tensor data from the fusion process after the multi-modal feature and weight variables of ML methodologies is far below than the natural tensor data.…”

Section: Introductionmentioning

confidence: 99%

cu_FastTucker: A Faster and Stabler Stochastic Optimization for Parallel Sparse Tucker Decomposition on Multi-GPUs

Li¹

2022

Preprint

View full text Add to dashboard Cite

High-Order, High-Dimension, and Sparse Tensor (HOHDST) data originates from real industrial applications, i.e., social networks, recommender systems, bio-information, and traffic information. Sparse Tensor Decomposition (STD) can project the HOHDST data into low-rank space. In this work, a novel method for STD of Kruskal approximating the core tensor and stochastic strategy for approximating the whole gradient is proposed which comprises of the following two parts: (1) the matrization unfolding order of the Kruskal product for the core tensor follows the multiplication order of the factor matrix and then the proposed theorem can reduce the exponential computational overhead into linear one; (2) stochastic strategy adopts one-step random sampling set, the volume of which is much smaller than original one, to approximate the whole gradient. Meanwhile, this method can guarantee the convergence and save the memory overhead. Due to the compactness of the same order matrix multiplication and parallel access from stochastic strategy, the speed of cuFastTucker can be further reinforced by GPU. Furthermore, a data division and communication strategy of cuFastTucker is proposed for data accommodation on Multi-GPU. cuFastTucker can achieve the fastest speed and keep the same accuracy and much lower memory overhead than the SOTA algorithms, e.g., P−Tucker, Vest, and SGD Tucker. The code and partial datasets are publically available on "https://github.com/ZixuanLi-China/FastTucker".

show abstract

“…For example, anomalous transactions indicate stolen credit cards. Hence, accurate identification of anomalous behavior is very important and has been widely used in several application areas, such as financial forecasting, 1 health‐care, 2 intrusion detection, 3,4 industrial damage, 5,6 sensor networks, 7 robot behavior, 8 astronomical data, 9 fraud detection, 10 and fault diagnosis 11,12 . Synonymously, anomaly detection is also termed as novelty, adverse behavior or deviation detection and exception mining.…”

Section: Introductionmentioning

confidence: 99%

One‐class tensor machine with randomized projection for large‐scale anomaly detection in high‐dimensional and noisy data

Razzak

Moustafa

Mumtaz

et al. 2021

Int J of Intelligent Sys

View full text Add to dashboard Cite

The modern industrial sector generates enormous amounts of high-dimensional heterogeneous data daily.However, mostly the vectored data (rank-one tensor) have been considered for anomaly detection, whereas the data in real-life is high dimensional. The expressive power of methods based on vector data is restrictive as they may destroy the structural information embedded in data and lead to the curse-of-dimensionality and overfitting. In this paper, we present a novel anomaly detection approach for large-scale tensor data. We first present novel one-class support tensor machines (OCSTM) with bounded loss function. We further extend it by leveraging the randomness to design a scalable approach that can also be used for large-scale anomaly detection. To solve the corresponding optimization of the objective function, we utilize half-quadratic optimization followed by solving it like a traditional OCSTM optimization at each iteration. We demonstrate the proposed randomized OCSTM with bounded hinge loss through experiments on 14 benchmark data sets. Experimental results demonstrate the effectiveness of the proposed approach against anomalies and a significant reduction in the computational complexity.

show abstract

Support Tensor Machine for Financial Forecasting

Cited by 13 publications

References 28 publications

Tensor-Train Recurrent Neural Networks for Interpretable Multi-Way Financial Forecasting

Tensor-Train Recurrent Neural Networks for Interpretable Multi-Way Financial Forecasting

cu_FastTucker: A Faster and Stabler Stochastic Optimization for Parallel Sparse Tucker Decomposition on Multi-GPUs

One‐class tensor machine with randomized projection for large‐scale anomaly detection in high‐dimensional and noisy data

Contact Info

Product

Resources

About