Liangyuan Guo
ABSTRACT
Virtual currency has been greeted with an avalanche of attention these days. In this case, allocate investments into traditional assets and virtual currency properly seems very important. In this paper, we select gold and bitcoin as our research objects, and select a series of representative indicators in the financial field. After data preprocessing, XGBoost algorithm is used to sort the importance of indicators, thus eliminating some unimportant indicators. Next, LSTM is used to predict the price of gold and bitcoin respectively. Therefore, the portfolio can be built based on it. In reality, trades often come with transaction costs. So we improve the Mean-Variance model considering the transaction costs, so as to get the initial portfolio strategy. On this basis, taking investment potential into account, we propose Traffic Light Signal(TLS) model, and successfully increasing the gross profit rate from 11.582% to 13.614%. Finally, we prove our portfolio model earns the highest returns by comparing it to other traditional portfolio models in terms of metrics Cumulative Yield, Annual Yield, and Max Drawdown Ratio.
- Eisl A, Gasser S , Weinmayer K. 2014. Caveat emptor: does bitcoin improve portfolio diversification?. Social Science Electronic Publishing.Google Scholar
- Devi D, Soekarno S. 2014. Alternative Investments Evaluation of Bitcoins. Gold and LQ45 Index. In International Conference on Trends in Economics, Humanities and Management (ICTEHM'14).Google Scholar
- Kim YB, Kim JG, Kim W, Im JH, Kim TH, Kang SJ, Kim CH. 2016. Predicting fluctuations in cryptocurrency transactions based on user comments and replies. PloS one.Google Scholar
- Giudici P, Pagnottoni P, Polinesi G. 2020. Network models to enhance automated cryptocurrency portfolio management. Frontiers in artificial intelligence.Google Scholar
- Shao, Xiaorui, and Chang Soo Kim. 2020. Multi-step short-term power consumption forecasting using multi-channel LSTM with time location considering customer behavior. IEEE.Google Scholar
- Xiao D, Yue Z, Ting L. 2015. Deep learning for event-driven stock prediction. International Conference on Artificial Intelligence.Google Scholar
- Chen K, Zhao Y, Dai F. 2015. A LSTM-based method for stock returns prediction:A case study of China stock market.IEEE.Google Scholar
- Fischer T, Krauss C. 2018. Deep learning with long short-term memory networks for financial market predictions. European Journal of Operational Research.Google Scholar
- Han Y , Yang K , Zhou G . 2013. A New Anomaly: The Cross-Sectional Profitability of Technical Analysis. Journal of Financial & Quantitative Analysis.Google ScholarCross Ref
- Mishra S. 2016. Technical Analysis and Risk Premium in Indian Equity Market: A Multiple Regression Analysis. IUP Journal of Applied Economics.Google Scholar
- Markowitz, HM. 1952. Portfolio Selection. the Journal of Finance.Google Scholar
- Brennan MJ. 1998. The role of learning in dynamic portfolio decisions. Review of Finance.Google Scholar
- Xia Y. 2001. Learning about predictability: The effects of parameter uncertainty on dynamic asset allocation. The Journal of Finance.Google ScholarCross Ref
- Brandt MW, Goyal A, Santa-Clara P, Stroud JR 2005. A simulation approach to dynamic portfolio choice with an application to learning about return predictability. The Review of Financial Studies.Google Scholar
- Hoevenaars RP, Molenaar RD, Schotman PC, Steenkamp TB. 2014. Strategic asset allocation for long‐term investors: Parameter uncertainty and prior information. Journal of Applied Econometrics.Google ScholarCross Ref
- Andrianto, Y, Diputra, Y. 2017. The effect of cryptocurrency on investment portfolio effectiveness. Journal of finance and accounting.Google ScholarCross Ref
- Nashirah Abu Bakar, Sofian Rosbi. 2018. Diversification Diagnostics for Portfolio Investing using Combination of Cryptocurrency and Stock Price. International Journal of Advanced Research.Google Scholar
- Ruey S. Tsay. 2012. An Introduction to Analysis of Financial Data with R .Google Scholar
- Sax C, Eddelbuettel D. 2018. ”Seasonal Adjustment by X-13ARIMA-SEATS in R.” Journal of Statistical Software.Google Scholar
- Song Wenzhu. 2019. Digital currency portfolio strategy research. PhD Thesis, Nanjing Information Engineering University.Google Scholar
Recommendations
Portfolio Choice with Illiquid Assets
We present a model of optimal allocation to liquid and illiquid assets, where illiquidity risk results from the restriction that an asset cannot be traded for intervals of uncertain duration. Illiquidity risk leads to increased and state-dependent risk ...
Optimal Combination of Currency Assets and Algorithm Simulation under Exchange Rate Risk
The excess money supply did not lead to a rapid rise in the price index, which in turn triggered inflation. In this case, the redetermination of the demand for money is particularly important. At the same time, with the continuous expansion of the capital ...
Comments