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

Algorithmic financial trading with deep convolutional neural networks: Time series to image conversion approach

Forecasting stock prices plays an important role in setting a trading strategy or determining the appropriate timing for buying or selling a stock. We propose a model, called the feature fusion long short-term memory-convolutional neural network (LSTM-CNN) model, that combines features learned from different representations of the same data, namely, stock time series and stock chart images, to predict stock prices. The proposed model is composed of LSTM and a CNN, which are utilized for extracting temporal features and image features. We measure the performance of the proposed model relative to those of single models (CNN and LSTM) using SPDR S&P 500 ETF data. Our feature fusion LSTM-CNN model outperforms the single models in predicting stock prices. In addition, we discover that a candlestick chart is the most appropriate stock chart image to use to forecast stock prices. Thus, this study shows that prediction error can be efficiently reduced by using a combination of temporal and image features from the same data rather than using these features separately.

/pdf/forecasting-stock-prices-with-a-feature-fusion-lstm-cnn-1rnbbijww3.pdf

Forecasting stock prices with a feature fusion LSTM-CNN model using different representations of the same data.

We develop a large-scale deep learning model to predict price movements from limit order book (LOB) data of cash equities. The architecture utilizes convolutional filters to capture the spatial structure of the LOBs as well as long short-term memory modules to capture longer time dependencies. The proposed network outperforms all existing state-of-the-art algorithms on the benchmark LOB dataset [A. Ntakaris, M. Magris, J. Kanniainen, M. Gabbouj, and A. Iosifidis, “Benchmark dataset for mid-price prediction of limit order book data with machine learning methods,” J. Forecasting , vol. 37, no. 8, 852–866, 2018]. In a more realistic setting, we test our model by using one-year market quotes from the London Stock Exchange, and the model delivers a remarkably stable out-of-sample prediction accuracy for a variety of instruments. Importantly, our model translates well to instruments that were not part of the training set, indicating the model's ability to extract universal features. In order to better understand these features and to go beyond a “black box” model, we perform a sensitivity analysis to understand the rationale behind the model predictions and reveal the components of LOBs that are most relevant. The ability to extract robust features that translate well to other instruments is an important property of our model, which has many other applications.

DeepLOB: Deep Convolutional Neural Networks for Limit Order Books

Deep Learning for Financial Applications : A Survey

A novel financial time-series analysis method based on deep learning technique is proposed in this paper. In recent years, the explosive growth of deep learning researches have led to several successful applications in various artificial intelligence and multimedia fields, such as visual recognition, robot vision, and natural language processing. In this paper, we focus on the time-series data processing and prediction in financial markets. Traditional feature extraction approaches in intelligent trading decision support system are used to applying several technical indicators and expert rules to extract numerical features. The major contribution of this paper is to improve the algorithmic trading framework with the proposed planar feature representation methods and deep convolutional neural networks (CNN). The proposed system is implemented and benchmarked in the historical datasets of Taiwan Stock Index Futures. The experimental results show that the deep learning technique is effective in our trading simulation application, and may have greater potentialities to model the noisy financial data and complex social science problems. In the future, we expected that the proposed methods and deep learning framework could be applied to more innovative applications in the next financial technology (FinTech) generation.

Financial Time-Series Data Analysis Using Deep Convolutional Neural Networks

Pairs trading is a statistical arbitrage strategy, which selects a set of assets with similar performance and produces profits during these asset prices far away from rational equilibrium. Once this phenomenon exists, traders can earn the spread by longing the underperforming asset and shorting the outperforming asset. This paper proposed a novel intelligent high-frequency pairs trading system in Taiwan Stock Index Futures (TX) and Mini Index Futures (MTX) market based on deep learning techniques. This research utilized the improved time series visualization method to transfer historical volatilities with different time frames into 2D images which are helpful in capturing arbitrage signals. Moreover, this research improved convolutional neural networks (CNN) model by combining the financial domain knowledge and filterbank mechanism. We proposed Filterbank CNN to extract high-quality features by replacing the random-generating filters with the arbitrage knowledge filters. In summary, the accuracy is enhanced through the proposed method, and it proves that the integrated information technology and financial knowledge could create the better pairs trading system.

Wei-Lun Chen

Papers

Financial Time-Series Data Analysis Using Deep Convolutional Neural Networks

Developing Arbitrage Strategy in High-frequency Pairs Trading with Filterbank CNN Algorithm