| Peer-Reviewed

Optimal Solution for the Gold Bitcoin Portfolio Investment Model

Received: 5 April 2023     Accepted: 31 March 2023     Published: 13 April 2023
Views:       Downloads:
Abstract

This topic is a portfolio investment problem with quantitative trading as the background. In order to solve this problem, three types of mathematical models are used in this paper, namely the prediction model, decision model, and risk assessment model. The first is the forecasting model. The paper applies three forecasting models: the grey system Grach (1, 1) forecasting model, the quadratic exponential smoothing forecasting model, and the time series BP-neural network forecasting model. The second is the decision-making model. The decision-making model in the paper is a constrained linear programming model. The objective function is to maximize the total revenue of the day. Finally, there is the risk assessment model. The quantitative investment and multi-factor models are used in the paper to calculate the standard deviation of the rate of return (conventional risk) of gold and Bitcoin respectively in a 30-day cycle, so as to achieve the purpose of quantifying risk, thus reflecting the relationship between gold and Bitcoin. The investment risk index of the two futures products of the currency is provided as a reference for investors. This paper also adjusts the parameters of the prediction model, such as adjusting the value of the number of neurons in the hidden layer of the BP-neural network, to compare the fitting effects corresponding to different parameters, to prove that the prediction model is an optimal solution; Give the decision-making model a certain disturbance, such as changing the definition of the objective function for the total return of the day, to reflect the performance of the forecasting model in dealing with the disturbance of special factors. After that, this paper also conducts a sensitivity analysis of the decision-making model. The specific method is to give a small disturbance to the decision-making model, such as changing its transaction cost, that is, the value of the commission rate a%, recording the final benefit of the decision-making model, and generating a chart to reflect the model. smoothness and sensitivity. Finally, this paper optimizes some models, such as optimizing the BP-neural network model by adaptively adjusting the learning rate and optimizing the linear programming decision model by adding the MACD information factor.

Published in Journal of Finance and Accounting (Volume 11, Issue 2)
DOI 10.11648/j.jfa.20231102.12
Page(s) 49-60
Creative Commons

This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.

Copyright

Copyright © The Author(s), 2023. Published by Science Publishing Group

Keywords

Exponential Smoothing, Time Series Model, Gray Model, Constrained Linear Programming Model, ARIMA Model, BP—Neural Network Model, MACD

References
[1] Wen Jing, Yin Chengyu, Liao Guowei, Wang Yuan, Zhang Jie. Application of GM (1,1) grey model to predict the incidence trend of thyroid cancer in China, Modern Oncology, mar. 2022.
[2] GDP prediction and analysis of Jiangsu Province Based on ARIMA model and BP neural network model [D]. Xu Mingyan Shandong University. 2020.
[3] Discussion on calculation method of regression coefficient of quadratic exponential smoothing prediction model [J] Chen Wu, Zhang Shanjiang, Hou Chunhua, Chen Chen, Zeng lichen Statistics and decision making 2016 (19).
[4] Mathematical modeling algorithm and application [M] National Defense Industry Press, Si Shoukui, 2011.
[5] Sensitivity analysis of changing constraints in linear programming [J] Liu Qijia, Xiao Yu Industry and Technology Forum 2021 (19).
[6] Application skills, defects and remedies of MACD index [J] Nie Shuyun Accounting of Chinese township enterprises. 2007 (04).
[7] Theoretical and empirical research on risk measurement method and financial asset allocation model [J] Wu Shi Nong, Chen Bin Economic research 1999 (09).
[8] 6.4.3.2. forecasting with single exponential smoothing. Available at: https://www.itl.nist.gov/div898/handbook/pmc/section4/pmc432.htm (Accessed: March 20, 2023).
[9] Frost, J. (2021) Exponential smoothing for time series forecasting, Statistics By Jim. Available at: https://statisticsbyjim.com/time-series/exponential-smoothing-time-series-forecasting/ (Accessed: March 20, 2023).
[10] Author links open overlay panelJie Cui a b et al. (2012) A novel grey forecasting model and its optimization, Applied Mathematical Modelling. Elsevier. Available at: https://www.sciencedirect.com/science/article/pii/S0307904X12005835 (Accessed: March 20, 2023).
[11] Application of quadratic exponential smoothing and Markov chain in... (no date). Available at: https://www.researchgate.net/publication/355098269_Application_of_Quadratic_Exponential_Smoothing_and_Markov_Chain_in_Computer_Predicting_Total_Amount (Accessed: March 20, 2023).
[12] Time series forecasting: Definition, applications, and examples (no date) Tableau. Available at: https://www.tableau.com/learn/articles/time-series-forecasting (Accessed: March 20, 2023).
[13] Author links open overlay panelLihong Yu and AbstractTaking kidney bean as the research object (2022) Optimization of BP neural network model by chaotic krill herd algorithm, Alexandria Engineering Journal. Elsevier. Available at: https://www.sciencedirect.com/science/article/pii/S1110016822001223#:~:text=The%20BP%20neural%20network%20model%20%28Back%20Propagation%29%20is,for%20information%20processing%20and%20has%20good%20predictive%20effect. (Accessed: March 20, 2023).
[14] Linear programming - definition, formula, problem, examples (no date) Cuemath. Available at: https://www.cuemath.com/algebra/linear-programming/ (Accessed: March 20, 2023).
[15] Hayes, A. (2023) Autoregressive integrated moving average (ARIMA) prediction model, Investopedia. Investopedia. Available at: https://www.investopedia.com/terms/a/autoregressive-integrated-moving-average-arima.asp (Accessed: March 20, 2023).
Cite This Article
  • APA Style

    Zihan Yang, Guanhua Zhang, Chuming Liu. (2023). Optimal Solution for the Gold Bitcoin Portfolio Investment Model. Journal of Finance and Accounting, 11(2), 49-60. https://doi.org/10.11648/j.jfa.20231102.12

    Copy | Download

    ACS Style

    Zihan Yang; Guanhua Zhang; Chuming Liu. Optimal Solution for the Gold Bitcoin Portfolio Investment Model. J. Finance Account. 2023, 11(2), 49-60. doi: 10.11648/j.jfa.20231102.12

    Copy | Download

    AMA Style

    Zihan Yang, Guanhua Zhang, Chuming Liu. Optimal Solution for the Gold Bitcoin Portfolio Investment Model. J Finance Account. 2023;11(2):49-60. doi: 10.11648/j.jfa.20231102.12

    Copy | Download

  • @article{10.11648/j.jfa.20231102.12,
      author = {Zihan Yang and Guanhua Zhang and Chuming Liu},
      title = {Optimal Solution for the Gold Bitcoin Portfolio Investment Model},
      journal = {Journal of Finance and Accounting},
      volume = {11},
      number = {2},
      pages = {49-60},
      doi = {10.11648/j.jfa.20231102.12},
      url = {https://doi.org/10.11648/j.jfa.20231102.12},
      eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.jfa.20231102.12},
      abstract = {This topic is a portfolio investment problem with quantitative trading as the background. In order to solve this problem, three types of mathematical models are used in this paper, namely the prediction model, decision model, and risk assessment model. The first is the forecasting model. The paper applies three forecasting models: the grey system Grach (1, 1) forecasting model, the quadratic exponential smoothing forecasting model, and the time series BP-neural network forecasting model. The second is the decision-making model. The decision-making model in the paper is a constrained linear programming model. The objective function is to maximize the total revenue of the day. Finally, there is the risk assessment model. The quantitative investment and multi-factor models are used in the paper to calculate the standard deviation of the rate of return (conventional risk) of gold and Bitcoin respectively in a 30-day cycle, so as to achieve the purpose of quantifying risk, thus reflecting the relationship between gold and Bitcoin. The investment risk index of the two futures products of the currency is provided as a reference for investors. This paper also adjusts the parameters of the prediction model, such as adjusting the value of the number of neurons in the hidden layer of the BP-neural network, to compare the fitting effects corresponding to different parameters, to prove that the prediction model is an optimal solution; Give the decision-making model a certain disturbance, such as changing the definition of the objective function for the total return of the day, to reflect the performance of the forecasting model in dealing with the disturbance of special factors. After that, this paper also conducts a sensitivity analysis of the decision-making model. The specific method is to give a small disturbance to the decision-making model, such as changing its transaction cost, that is, the value of the commission rate a%, recording the final benefit of the decision-making model, and generating a chart to reflect the model. smoothness and sensitivity. Finally, this paper optimizes some models, such as optimizing the BP-neural network model by adaptively adjusting the learning rate and optimizing the linear programming decision model by adding the MACD information factor.},
     year = {2023}
    }
    

    Copy | Download

  • TY  - JOUR
    T1  - Optimal Solution for the Gold Bitcoin Portfolio Investment Model
    AU  - Zihan Yang
    AU  - Guanhua Zhang
    AU  - Chuming Liu
    Y1  - 2023/04/13
    PY  - 2023
    N1  - https://doi.org/10.11648/j.jfa.20231102.12
    DO  - 10.11648/j.jfa.20231102.12
    T2  - Journal of Finance and Accounting
    JF  - Journal of Finance and Accounting
    JO  - Journal of Finance and Accounting
    SP  - 49
    EP  - 60
    PB  - Science Publishing Group
    SN  - 2330-7323
    UR  - https://doi.org/10.11648/j.jfa.20231102.12
    AB  - This topic is a portfolio investment problem with quantitative trading as the background. In order to solve this problem, three types of mathematical models are used in this paper, namely the prediction model, decision model, and risk assessment model. The first is the forecasting model. The paper applies three forecasting models: the grey system Grach (1, 1) forecasting model, the quadratic exponential smoothing forecasting model, and the time series BP-neural network forecasting model. The second is the decision-making model. The decision-making model in the paper is a constrained linear programming model. The objective function is to maximize the total revenue of the day. Finally, there is the risk assessment model. The quantitative investment and multi-factor models are used in the paper to calculate the standard deviation of the rate of return (conventional risk) of gold and Bitcoin respectively in a 30-day cycle, so as to achieve the purpose of quantifying risk, thus reflecting the relationship between gold and Bitcoin. The investment risk index of the two futures products of the currency is provided as a reference for investors. This paper also adjusts the parameters of the prediction model, such as adjusting the value of the number of neurons in the hidden layer of the BP-neural network, to compare the fitting effects corresponding to different parameters, to prove that the prediction model is an optimal solution; Give the decision-making model a certain disturbance, such as changing the definition of the objective function for the total return of the day, to reflect the performance of the forecasting model in dealing with the disturbance of special factors. After that, this paper also conducts a sensitivity analysis of the decision-making model. The specific method is to give a small disturbance to the decision-making model, such as changing its transaction cost, that is, the value of the commission rate a%, recording the final benefit of the decision-making model, and generating a chart to reflect the model. smoothness and sensitivity. Finally, this paper optimizes some models, such as optimizing the BP-neural network model by adaptively adjusting the learning rate and optimizing the linear programming decision model by adding the MACD information factor.
    VL  - 11
    IS  - 2
    ER  - 

    Copy | Download

Author Information
  • Queen Mary University of London Engineering School, Northwestern Polytechnical University, Xi 'an, China

  • Queen Mary University of London Engineering School, Northwestern Polytechnical University, Xi 'an, China

  • Queen Mary University of London Engineering School, Northwestern Polytechnical University, Xi 'an, China

  • Sections