Selecting dynamic moving average trading rules in the crude oil futures market using a genetic approach

被引：26

作者：

Wang, Lijun ^{[1
,2
]}

An, Haizhong ^{[1
,2
,3
]}

Liu, Xiaojia ^{[1
,2
]}

Huang, Xuan ^{[1
,2
]}

机构：

[1] China Univ Geosci, Sch Humanities & Econ Management, Beijing 100083, Peoples R China

[2] Minist Land & Resources, Key Lab Carrying Capac Assessment Resource & Envi, Beijing 100083, Peoples R China

[3] China Univ Geosci, Lab Resources & Environm Management, Beijing 100083, Peoples R China

来源：

APPLIED ENERGY | 2016年 / 162卷

关键词：

Crude oil futures market; Genetic algorithm; Technical analysis; Moving average trading rules; ARTIFICIAL NEURAL-NETWORKS; TECHNICAL ANALYSIS; PRICE DISCOVERY; P; 500; PROFITABILITY; PERFORMANCE; ALGORITHMS; STRATEGIES; PREDICTION; EFFICIENCY;

D O I：

10.1016/j.apenergy.2015.08.132

中图分类号：

TE [石油、天然气工业]; TK [能源与动力工程];

学科分类号：

0807 ; 0820 ;

摘要：

Strategies to increase profit from investments in crude oil futures markets are an important issue for investors in energy finance. This paper proposes an approach to generate dynamic moving average trading rules in crude oil futures markets. An adaptive moving average calculation is used to better describe the fluctuations, and trading rules can be adjusted dynamically in the investment period based on the performance of four reference rules. We use genetic algorithms to select optimal dynamic moving average trading rules from a large set of possible parameters. Our results indicate that dynamic trading rules can help traders make profit in the crude oil futures market and are more effective than the BH strategy in the price decrease process. Moreover, dynamic moving average trading rules are more favorable to traders than static trading rules, and the advantage becomes more obvious over long investment cycles. The lengths of the two periods of dynamic moving average trading rules are closely associated with price volatility. The dynamic trading rules will have outstanding performance when market is shocked by significant energy related events. Investment advices are given out and these advices are helpful for traders when choosing technical trading rules in actual investments. (C) 2015 Elsevier Ltd. All rights reserved.

引用

页码：1608 / 1618

页数：11

共 88 条

[81] Testing the evolution of crude oil market efficiency: Data have the conn [J].

Zhang, Bing ;

Li, Xiao-Ming ;

He, Fei .

ENERGY POLICY, 2014, 68 :39-52

[82] Forecasting with artificial neural networks: The state of the art [J].

Zhang, GQ ;

Patuwo, BE ;

Hu, MY .

INTERNATIONAL JOURNAL OF FORECASTING, 1998, 14 (01) :35-62

[83] Particle Swarm Optimization Algorithm for Agent-Based Artificial Markets [J].

Zhang, Tong ;

Brorsen, B. Wade .

COMPUTATIONAL ECONOMICS, 2009, 34 (04) :399-417

[84] Stock market prediction of S&P 500 via combination of improved BCO approach and BP neural network [J].

Zhang Yudong ;

Wu Lenan .

EXPERT SYSTEMS WITH APPLICATIONS, 2009, 36 (05) :8849-8854

[85] Interpreting the crude oil price movements: Evidence from the Markov regime switching model [J].

Zhang, Yue-Jun ;

Zhang, Lu .

APPLIED ENERGY, 2015, 143 :96-109

[86] Speculative trading and WTI crude oil futures price movement: An empirical analysis [J].

Zhang, Yue-Jun .

APPLIED ENERGY, 2013, 107 :394-402

[87] Investigating the price discovery and risk transfer functions in the crude oil and gasoline futures markets: Some empirical evidence [J].

Zhang, Yue-Jun ;

Wang, Zi-Yi .

APPLIED ENERGY, 2013, 104 :220-228

[88] Particle Swarm Optimization (PSO) for the constrained portfolio optimization problem [J].

Zhu, Hanhong ;

Wang, Yi ;

Wang, Kesheng ;

Chen, Yun .

EXPERT SYSTEMS WITH APPLICATIONS, 2011, 38 (08) :10161-10169

← 1 2 3 4 5 6 7 8 9 →