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

Jerzy Korczak , Marcin Hernes

Abstract

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 and evaluation of a deep learning model implemented using H20 library as an agent of A-Trader system
Author Jerzy Korczak (MISaF / IBI / DIT)
Jerzy Korczak,,
- Department of Information Technologies
, Marcin Hernes (EaE / IES / DACIaQM)
Marcin Hernes,,
- Department of Accounting, Control, Informatics and Quantitative Methods
Pages905-912
Publication size in sheets0.5
Book Ganzha Maria, Maciaszek Leszek, Paprzycki Marcin (eds.): Proceedings of the 2017 Federated Conference on Computer Science and Information Systems, Annals of Computer Science and Information Systems, vol. 11, 2017, Polskie Towarzystwo Informatyczne, Institute of Electrical and Electronics Engineers , ISBN 978-83-946253-9-9, [978-83-946253-8-2, 978-83-946253-7-5], 1398 p., DOI:10.15439/978-83-946253-7-5
DOIDOI:10.15439/2017F449
URL https://annals-csis.org/proceedings/2017/pliks/fedcsis.pdf
Languageen angielski
File
Hernes_Korczak_Deep_Learning_ for_ Financial_ Time2017.pdf 631,26 KB
Score (nominal)15
ScoreMinisterial score = 15.0, 02-07-2019, ChapterFromConference
Citation count*14 (2019-12-14)
Cite
Share Share

Get link to the record


* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.
Back