Forecasting Stock Prices from the Limit Order Book Using Convolutional Neural Networks

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

doi:10.1109/cbi.2017.23

Cited by 269 publications

(176 citation statements)

References 8 publications

Supporting

Mentioning

153

Contrasting

Unclassified

Order By: Relevance

“…Although being deep with 7 hidden layers, the CNN model is greatly inferior to the proposed ones. Here we should note that the CNN proposed in [47] gradually extracts local temporal information by the convolution layers. On the other hand, the evaluated bilinear structures fuse global temporal information from the beginning, i.e.…”

Section: Experiments Resultsmentioning

confidence: 99%

“…The insights into the attention patterns and the amount of attention received by each event given by the proposed attention-based layer could facilitate further quantitative analysis such as casualty or pseudo-period analysis. Table III reports the average computation time of C(BL), C(TABL), CNN [47], LSTM [48] measured on the same machine with CPU core i7-4790 and 32 GB of memory. The second, third and last column shows the average time (in millisecond) taken by the forward pass, backward pass and one training pass of a single sample in the state-of-the-art models.…”

Section: Experiments Resultsmentioning

confidence: 99%

“…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 3 more Smart Citations

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

198

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: Experiments Resultsmentioning

confidence: 99%

Section: Experiments Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

198

117

View full text Add to dashboard Cite

show abstract

“…CNN models with different data representations were also used for trend prediction. In [219], the authors used the last 100 entries from the limit order book to create images for the stock price prediction using CNN. Using the limit order book data to create 2D matrixlike format with CNN for predicting directional movement was innovative.…”

Section: Trend Forecastingmentioning

confidence: 99%

Financial time series forecasting with deep learning : A systematic literature review: 2005–2019

Sezer

Gudelek

Özbayoğlu

2020

Applied Soft Computing

795

294

View full text Add to dashboard Cite

Financial time series forecasting is, without a doubt, the top choice of computational intelligence for finance researchers from both academia and financial industry due to its broad implementation areas and substantial impact. Machine Learning (ML) researchers came up with various models and a vast number of studies have been published accordingly. As such, a significant amount of surveys exist covering ML for financial time series forecasting studies. Lately, Deep Learning (DL) models started appearing within the field, with results that significantly outperform traditional ML counterparts. Even though there is a growing interest in developing models for financial time series forecasting research, there is a lack of review papers that were solely focused on DL for finance. Hence, our motivation in this paper is to provide a comprehensive literature review on DL studies for financial time series forecasting implementations. We not only categorized the studies according to their intended forecasting implementation areas, such as index, forex, commodity forecasting, but also grouped them based on their DL model choices, such as Convolutional Neural Networks (CNNs), Deep Belief Networks (DBNs), Long-Short Term Memory (LSTM). We also tried to envision the future for the field by highlighting the possible setbacks and opportunities, so the interested researchers can benefit.

show abstract

Bibliography

2021

Machine Learning for Risk Calculations

View full text Add to dashboard Cite

Forecasting Stock Prices from the Limit Order Book Using Convolutional Neural Networks

Cited by 269 publications

References 8 publications

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

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

Financial time series forecasting with deep learning : A systematic literature review: 2005–2019

Bibliography

Contact Info

Product

Resources

About