Using deep learning to detect price change indications in financial markets

Tsantekidis, Avraam; Passalis, Nikolaos; Tefas, Anastasios; Kanniainen, Juho; Gabbouj, Moncef; Iosifidis, Alexandros

doi:10.23919/eusipco.2017.8081663

Cited by 112 publications

(88 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to the erratic, noisy nature of stock price movement, many deep neural networks were proposed within a complex forecasting pipeline. For example, in high-frequency LOB data, the authors proposed to normalize the LOB states by the prior date's statistics before feeding them to a CNN [47] or an LSTM network [48]. A more elaborate pipeline consisting of multiresolution wavelet transform to filter the noisy input series, stacked Auto-Encoder to extract high-level representation of each stock index and an LSTM network to predict future prices was recently proposed in [54].…”

Section: Related Workmentioning

confidence: 99%

“…In recent work [46], we have showed that a linear multivariate regression model could outperform other competing shallow architectures that do not take into account the temporal nature of HFT data. While performing reasonably well compared to other shallow architectures, the learning model in [46] has certain short-comings in practice: the analytical solution is computed based on the entire dataset prohibiting its application in an online learning scenario; with large amount of data, this model clearly underfits the underlying generating process with performance inferior to other models based on deep architectures [47], [48]. In this work, we propose a neural network layer which incorporates the idea of bilinear projection in order to learn two separate dependencies for the two modes of multivariate time-series data.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Temporal Attention-Augmented Bilinear Network for Financial Time-Series Data Analysis

Tran

Iosifidis

Kanniainen

et al. 2019

IEEE Trans. Neural Netw. Learning Syst.

Self Cite

190

117

View full text Add to dashboard Cite

Financial time-series forecasting has long been a challenging problem because of the inherently noisy and stochastic nature of the market. In the High-Frequency Trading (HFT), forecasting for trading purposes is even a more challenging task since an automated inference system is required to be both accurate and fast. In this paper, we propose a neural network layer architecture that incorporates the idea of bilinear projection as well as an attention mechanism that enables the layer to detect and focus on crucial temporal information. The resulting network is highly interpretable, given its ability to highlight the importance and contribution of each temporal instance, thus allowing further analysis on the time instances of interest. Our experiments in a large-scale Limit Order Book (LOB) dataset show that a two-hidden-layer network utilizing our proposed layer outperforms by a large margin all existing state-of-the-art results coming from much deeper architectures while requiring far fewer computations.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Temporal Attention-Augmented Bilinear Network for Financial Time-Series Data Analysis

Tran

Iosifidis

Kanniainen

et al. 2019

IEEE Trans. Neural Netw. Learning Syst.

Self Cite

190

117

View full text Add to dashboard Cite

show abstract

“…Makinen et al [37] predict price jumps with the use of LSTM, where the input data is based on LOB data. A similar work, in terms of the neural model, is conducted in [53] in order to forecast LOB's mid-price.…”

Section: Literature Reviewmentioning

confidence: 99%

Feature Engineering for Mid-Price Prediction With Deep Learning

et al. 2019

Self Cite

View full text Add to dashboard Cite

Mid-price movement prediction based on limit order book data is a challenging task due to the complexity and dynamics of the limit order book. So far, there have been very limited attempts for extracting relevant features based on limit order book data. In this paper, we address this problem by designing a new set of handcrafted features and performing an extensive experimental evaluation on both liquid and illiquid stocks. More specifically, we present an extensive set of econometric features that capture statistical properties of the underlying securities for the task of mid-price prediction. The experimental evaluation consists of a head-to-head comparison with other handcrafted features from the literature and with features extracted from a long short-term memory autoencoder by means of a fully automated process. Moreover, we develop a new experimental protocol for online learning that treats the task above as a multi-objective optimization problem and predicts i) the direction of the next price movement and ii) the number of order book events that occur until the change takes place. In order to predict the mid-price movement, features are fed into nine different deep learning models based on multi-layer perceptrons, convolutional neural networks, and long short-term memory neural networks. The performance of the proposed method is then evaluated on liquid and illiquid stocks (i.e., TotalView-ITCH US and Nordic stocks). For some stocks, results suggest that the correct choice of a feature set and a model can lead to the successful prediction of how long it takes to have a stock price movement.

show abstract

“…Forecasting time series is an increasingly important topic, with several applications in various domains [1], [5], [13], [15], [16], [19], [23], [34]. Many of these tasks are nowadays tackled using powerful deep learning (DL) models [6], [8], [14], [29], [31], which often lead to state-of-the-art results outperforming the previously used methods. However, applying deep learning models to time series is challenging due to the non-stationary and multimodal nature of the data.…”

Section: Introductionmentioning

confidence: 99%

Deep Adaptive Input Normalization for Time Series Forecasting

Passalis

Tefas

Kanniainen

et al. 2020

IEEE Trans. Neural Netw. Learning Syst.

Self Cite

View full text Add to dashboard Cite

Deep Learning (DL) models can be used to tackle time series analysis tasks with great success. However, the performance of DL models can degenerate rapidly if the data are not appropriately normalized. This issue is even more apparent when DL is used for financial time series forecasting tasks, where the non-stationary and multimodal nature of the data pose significant challenges and severely affect the performance of DL models. In this work, a simple, yet effective, neural layer, that is capable of adaptively normalizing the input time series, while taking into account the distribution of the data, is proposed. The proposed layer is trained in an end-to-end fashion using back-propagation and leads to significant performance improvements compared to other evaluated normalization schemes. The proposed method differs from traditional normalization methods since it learns how to perform normalization for a given task instead of using a fixed normalization scheme. At the same time, it can be directly applied to any new time series without requiring re-training. The effectiveness of the proposed method is demonstrated using a large-scale limit order book dataset, as well as a load forecasting dataset.

show abstract

Using deep learning to detect price change indications in financial markets

Cited by 112 publications

References 11 publications

Temporal Attention-Augmented Bilinear Network for Financial Time-Series Data Analysis

Temporal Attention-Augmented Bilinear Network for Financial Time-Series Data Analysis

Feature Engineering for Mid-Price Prediction With Deep Learning

Deep Adaptive Input Normalization for Time Series Forecasting

Contact Info

Product

Resources

About