A multi-model approach to the development of algorithmic trading systems for the Forex market

被引:0
|
作者
Sevastjanov, Pavel [1 ]
Kaczmarek, Krzysztof [2 ]
Rutkowski, Leszek [3 ,4 ]
机构
[1] Social Sci Acad, Henryka Sienkiewicza 9, PL-90113 Lodz, Poland
[2] Czestochowa Tech Univ, Dept Comp Sci, Dabrowskiego 73, PL-42201 Czestochowa, Poland
[3] Polish Acad Sci, Syst Res Inst, PL-01447 Warsaw, Poland
[4] AGH Univ Sci & Technol, Inst Comp Sci, PL-30059 Krakow, Poland
关键词
Technical analysis; Multi-model approach; Algorithmic trading system; Forex;
D O I
10.1016/j.eswa.2023.121310
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In the decade passed, considerable affords were made to develop effective trading systems based on different assumptions concerned with the market nature, methods for data processing and uncertainty modeling. Such systems are often so sophisticated that they can be applied only by their authors. Another limitation of them is concerned with the focus on the development of a universal single best model. Besides, any model works well only in limited time periods and fails when noticeable changes in the market behavior occur. Then a major revision or the development of a new model is inevitable. Unfortunately, usually this needs too much time. Therefore, in this paper, to avoid the above problems, the simple multi-model approach to the development of trading systems in the Forex market is proposed. It is based on some working hypotheses, which are justified in this paper. The first of them is based on the observation that the Forex is the aggregation of numerous streams (strategies) provided by the broad trades community. Therefore, we can expect that even a very simple model based on the particular trading idea or ideas may catch such a string to be profitable, at least during a small period. If we have developed a set of such simple models optimized for different currency pairs, in each trading period we can use the model providing maximal profit for a certain currency pair. The profitability of the proposed approach is illustrated by the trading results obtained on the symbols EURUSD,GBPUSD, AUDUSD and USDJPY for the timeframes H1 and H4 with the use of the Meta Trader 4 platform.
引用
收藏
页数:26
相关论文
共 50 条
  • [1] Analysis of Algorithmic Trading with Q-Learning in the Forex Market
    Grover, Aruquipa A.
    Gabriel, Rojas S.
    [J]. 2021 INTERNATIONAL CONFERENCE ON EMERGING SMART COMPUTING AND INFORMATICS (ESCI), 2021, : 73 - 77
  • [2] Multi-agent platform to support trading decisions in the FOREX market
    Hernes, Marcin
    Korczak, Jerzy
    Krol, Dariusz
    Pondel, Maciej
    Becker, Joerg
    [J]. APPLIED INTELLIGENCE, 2024, 54 (22) : 11690 - 11708
  • [3] Outperforming algorithmic trading reinforcement learning systems: A supervised approach to the cryptocurrency market
    Felizardo, Leonardo Kanashiro
    Lima Paiva, Francisco Caio
    Graves, Catharine de Vita
    Matsumoto, Elia Yathie
    Reali Costa, Anna Helena
    Del-Moral-Hernandez, Emilio
    Brandimarte, Paolo
    [J]. EXPERT SYSTEMS WITH APPLICATIONS, 2022, 202
  • [4] The role of algorithmic trading systems on stock market efficiency
    Ji-Yong Seo
    Sangmi Chai
    [J]. Information Systems Frontiers, 2013, 15 : 873 - 888
  • [5] The role of algorithmic trading systems on stock market efficiency
    Seo, Ji-Yong
    Chai, Sangmi
    [J]. INFORMATION SYSTEMS FRONTIERS, 2013, 15 (05) : 873 - 888
  • [6] A multi-model approach to investigate security of supply in the German electricity market
    Hladik, Dirk
    Fraunholz, Christoph
    Manz, Pia
    Keuhnbach, Matthias
    Kunze, Robert
    [J]. 2018 15TH INTERNATIONAL CONFERENCE ON THE EUROPEAN ENERGY MARKET (EEM), 2018,
  • [7] Multi-model approach to model selection
    Stoica, P
    Selén, Y
    Jian, L
    [J]. DIGITAL SIGNAL PROCESSING, 2004, 14 (05) : 399 - 412
  • [8] The multi-model approach for fractional-order systems modelling
    Talmoudi, Samia
    Lahmari, Moufida
    [J]. TRANSACTIONS OF THE INSTITUTE OF MEASUREMENT AND CONTROL, 2018, 40 (01) : 331 - 340
  • [9] A multi-model modeling approach to nonlinear systems based on lazy learning
    Pan Tianhong
    Li Shaoyuan
    Wang Xin
    [J]. Proceedings of the 24th Chinese Control Conference, Vols 1 and 2, 2005, : 268 - 273
  • [10] A Multi-Model Approach to Nucleic Acid-Based Drug Development
    Isabelle Gautherot
    Regís Sodoyer
    [J]. BioDrugs, 2004, 18 : 37 - 50