Deep Learning for Financial Time Series Forecasting in A-Trader System

Jerzy Korczak, Marcin Hernes
2017 Proceedings of the 2017 Federated Conference on Computer Science and Information Systems  
The paper presents aspects related to developing methods for financial time series forecasting using deep learning in relation to multi-agent stock trading system, called A-Trader. On the basis of this model, an investment strategies in A-Trader system can be build. The first part of the paper briefly discusses a problem of financial time series on FOREX market. Classical neural networks and deep learning models are outlined, their performances are analyzed. The final part presents deployment
more » ... d evaluation of a deep learning model implemented using H20 library as an agent of A-Trader system.
doi:10.15439/2017f449 dblp:conf/fedcsis/KorczakH17 fatcat:umga7i5fq5ax7ejx77c3ahrkja