Research on Transaction Strategy Based on BP Neural Network
DOI: 10.23977/ferm.2022.050208 | Downloads: 13 | Views: 632
Author(s)
Zehan Wang 1, Rongrong Guo 1, Yunhang Ma 1
Affiliation(s)
1 Data Science and Artificial Intelligence Faculty, Dongbei University of Finance and Economics, Dalian, Liaoning, 116025, China
Corresponding Author
Zehan WangABSTRACT
In this paper, in order to develop the best trading strategy, we need to predict the data first. BP neural network and sliding prediction method are adopted. The neural network is trained based on the data of the first seven days and then used to predict future prices. The expected rate of return is calculated based on the predicted value. Use the expected rate of return to calculate future returns and maximize them as the first goal. The standard deviation of past returns is used as the risk factor. Minimizing future risk is the second goal. As a constraint, the total value of assets in each transaction remains unchanged. Establish a multi-objective programming model. By introducing risk preference, the multi-objective programming problem is transformed into a single-objective programming problem. In this system, predictions and decisions are made again and again. At the same time, considering the two situations in which gold cannot be traded when the market is closed, trading is not recommended when the price of bitcoin fluctuates too much.
KEYWORDS
Neural network, Forecast, The best strategyCITE THIS PAPER
Zehan Wang, Rongrong Guo, Yunhang Ma, Research on Transaction Strategy Based on BP Neural Network. Financial Engineering and Risk Management (2022) Vol. 5: 47-52. DOI: http://dx.doi.org/10.23977/ferm.2022.050208.
REFERENCES
[1] Chen Keyan. Research on the optimal portfolio investment model based on genetic algorithm [D]. Nanjing Meteorological Institute, 2004.
[2] Wu Shigang, Meng Xianli, Hu Ang. Portfolio Model [J]. Practice and Understanding of Mathematics, 1999(01): 15-18.
[3] The calculation formula of meaning square error comes from: https://blog.csdn.net/guolindonggld/article/details /87856780.
[4] Zhang Jun, Zeng Bo, Meng Wei Test method of interval grey numerical prediction model error [J] Statistics and decision making, 2014 (16): 17-19.
[5] Annual rate of return and annualized rate of return [J] Home technology, 2019 (5).
[6] The annualized rate of return data comes from: https://fund.jrj.com.cn/funddata/yield.shtml.
Downloads: | 16234 |
---|---|
Visits: | 334446 |
Sponsors, Associates, and Links
-
Information Systems and Economics
-
Accounting, Auditing and Finance
-
Industrial Engineering and Innovation Management
-
Tourism Management and Technology Economy
-
Journal of Computational and Financial Econometrics
-
Accounting and Corporate Management
-
Social Security and Administration Management
-
Population, Resources & Environmental Economics
-
Statistics & Quantitative Economics
-
Agricultural & Forestry Economics and Management
-
Social Medicine and Health Management
-
Land Resource Management
-
Information, Library and Archival Science
-
Journal of Human Resource Development
-
Manufacturing and Service Operations Management
-
Operational Research and Cybernetics