Neural networks in financial trading

被引:19
作者
Sermpinis, Georgios [1 ]
Karathanasopoulos, Andreas [2 ]
Rosillo, Rafael [3 ]
de la Fuente, David [4 ]
机构
[1] Univ Glasgow, Business Sch, Adam Smith Bldg, Glasgow G12 8QQ, Lanark, Scotland
[2] Univ Dubai, Dubai Business Sch, Dubai 14143, U Arab Emirates
[3] Univ Oviedo, Business & Management Dept, Campus Viesques S-N, Gijon 33204, Spain
[4] Univ Oviedo, Business & Management Dept, Campus Viesques S-N, Oviedo 33204, Spain
关键词
Neural networks; Forecasting; Trading; Multiple hypothesis testing;
D O I
10.1007/s10479-019-03144-y
中图分类号
C93 [管理学]; O22 [运筹学];
学科分类号
070105 ; 12 ; 1201 ; 1202 ; 120202 ;
摘要
In this study, we generate 50 Multi-layer Perceptons, 50 Radial Basis Functions, 50 Higher Order Neural Networks and 50 Recurrent Neural Network and we explore their utility in forecasting and trading the DJIA, NASDAQ 100 and the NIKKEI 225 stock indices. The statistical significance of the forecasts is examined through the False Discovery Ratio of Bajgrowicz and Scaillet (J Financ Econ 106(3):473-491, 2012). Two financial everages, based on the levels of financial stress and the financial volatility respectively, are also applied. In terms of the results, we note that RNN have the higher percentage of significant models and present the stronger profitability compared to their Neural Network counterparts. The financial leverages doubles the trading performance of our models.
引用
收藏
页码:293 / 308
页数:16
相关论文
共 43 条
[1]   MLP ensembles improve long term prediction accuracy over single networks [J].
Adeodato, Paulo J. L. ;
Arnaud, Adrian L. ;
Vasconcelos, Germano C. ;
Cunha, Rodrigo C. L. V. ;
Monteiro, Domingos S. M. P. .
INTERNATIONAL JOURNAL OF FORECASTING, 2011, 27 (03) :661-671
[2]   Pricing and trading European options by combining artificial neural networks and parametric models with implied parameters [J].
Andreou, Panayiotis C. ;
Charalambous, Chris ;
Martzoukos, Spiros H. .
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH, 2008, 185 (03) :1415-1433
[3]   Financial forecasting using ANFIS networks with Quantum-behaved Particle Swarm Optimization [J].
Bagheri, Ahmad ;
Peyhani, Hamed Mohammadi ;
Akbari, Mohsen .
EXPERT SYSTEMS WITH APPLICATIONS, 2014, 41 (14) :6235-6250
[4]   A comparative survey of artificial intelligence applications in finance: artificial neural networks, expert system and hybrid intelligent systems [J].
Bahrammirzaee, Arash .
NEURAL COMPUTING & APPLICATIONS, 2010, 19 (08) :1165-1195
[5]   Technical trading revisited: False discoveries, persistence tests, and transaction costs [J].
Bajgrowicz, Pierre ;
Scaillet, Olivier .
JOURNAL OF FINANCIAL ECONOMICS, 2012, 106 (03) :473-491
[6]   Direction-of-change forecasting using a volatility-based recurrent neural network [J].
Bekiros, S. D. ;
Georgoutsos, D. A. .
JOURNAL OF FORECASTING, 2008, 27 (05) :407-417
[7]  
Bertolini L., 2010, THESIS CITY U LONDON
[8]  
Boston Consulting Group, 2016, FACT FUT GHOST MACH
[9]  
Broomhead D.S., 1988, Memorandum 4148
[10]   Computational Intelligence and Financial Markets: A Survey and Future Directions [J].
Cavalcante, Rodolfo C. ;
Brasileiro, Rodrigo C. ;
Souza, Victor L. P. ;
Nobrega, Jarley P. ;
Oliveira, Adriano L. I. .
EXPERT SYSTEMS WITH APPLICATIONS, 2016, 55 :194-211