International Conference on Computer and Knowledge Engineering

Home / 12th International Conference on Computer and Knowledge Engineering

Financial Market Prediction Using Deep Neural Networks with Hardware Acceleration

Authors :

Dara Rahmati¹ Mohammad Hadi Foroughi² Ali Bagherzadeh³ Mehdi Foroughi⁴ Saeid Gorgin⁵

1- Assistant Professor, CSE Department, Shahid Beheshti University 2- Computer Engineering Student, Shahid Beheshti University 3- Computer Engineering Student, Shahid Beheshti University 4- Department of Informatics, University of Oslo 5- Iranian Research Organization for Science and Technology (IROST), Tehran, Iran and Chosun University, South Korea

Keywords :

Financial Market،FPGA،Prediction،Field programmable gate array،Deep Learning،Hardware Acceleration،Convolution،MLP

Abstract :

Financial market prediction has long been a hard-to-solve problem. Recently many machine learning and deep learning approaches have been taken into account to predict various properties of financial markets, namely volatility, price, and trend prediction. This paper proposes a novel multi-time-frame 1-D convolutional neural network to predict market movements. The model is trained with actual foreign exchange data in an offline setting. The trained model is then deployed on a Xilinx Zedboard Zynq-7000 SoC field programmable gate array (FPGA) to accelerate the calculation and also reducing the power consumption compared to the known approaches. We evaluate the performance of our model on test-set data new to the model; the results show that the proposed model outperforms commonly used models such as long short term memory (LSTM), multi-layer perceptron (MLP), and single-time-scale convolutional neural networks (CNN) with an accuracy of 76.60%. Although deploying the model on FPGA causes a slight accuracy reduction of 2.56%, the evaluations show that the accuracy of the hardware model is still higher than other models. Moreover, according to the evaluation results, performing the inference phase on hardware dramatically reduces latency which is a vital feature for this kind of applications with a factor of roughly 380. Power consumption is also compared and reduced when compared to an Intel server with Xeon ES-2658 processor.