Chenfeng Xie
ABSTRACT
In this paper, we study the price changes of bitcoin and gold over time by building an LSTM-based price prediction model and a genetic algorithm-based yield optimization model. Specifically, we build a two-layer LSTM-based time series forecasting model. In order to study how to make decisions on capital allocation and profit maximization, a single-objective optimization model based on a genetic algorithm is established. Furthermore, to prove that our decision model is optimal, we use the error evaluation metrics MSE, MAE, and R2 to perform statistical analysis on the predicted asset value and the actual asset value, where R2 reaches 0.8857. Finally, we perform a sensitivity analysis on transaction commissions.
- Z. Ning, F. J. Wen, Z. Y. Xuan, "Bitcoin price prediction based on LSTM hybrid model ," Computer Science,2021,48(S2):39-45.Google Scholar
- F. Xiang, Q. L. Hui, G. X. Ran, "Recognition method of student feed-back text academic emotion based on LSTM model," Open Education Research, 2019,25(02):114-120.Google Scholar
- L. J. Ping, "Research on stock trend prediction based on double-layer LSTM model," Science and Technology and Innovation, 2021, (07): 50-51.Google Scholar
- L. Lu, L. Lei, L. X. Jun, S. S. Zhi, "Comparative research on COMEX gold futures price prediction based on LSTM," Journal of Changchun University of Science and Technology(Natural Science Edition), 2021,44(02):129-135.Google Scholar
- C. D. Greene, "On the origin of species," Peking University Press, 2018.Google Scholar
- G. Ya, "Research on stock market forecasting model based on RS-LS-SVM," Chengdu University of Technology, 2017.Google Scholar
- R Squared Formula. [Online]. Available: https://www.wallstreetmojo.com/r-squared-form ula/.Google Scholar
Index Terms
- Optimal Strategy: A Comprehensive Model for Predicting Price Trend and Algorithm Optimization
Recommendations
Predicting Stock Market Price Using Neural Network Model
The present article predicts the movement of daily Indian stock market S&P CNX Nifty price by using Feedforward Neural Network Model over a period of eight years from January 1st 2008 to April 8th 2016. The prediction accuracy of the model is accessed ...
A real time clustering and SVM based price-volatility prediction for optimal trading strategy
Financial return on investments and movement of market indicators are fraught with uncertainties and a highly volatile environment that exists in the global market. Equity markets are heavily affected by market unpredictability and maintaining a healthy ...
Price Trend Prediction of Stock Market Using Outlier Data Mining Algorithm
BDCLOUD '15: Proceedings of the 2015 IEEE Fifth International Conference on Big Data and Cloud ComputingIn this paper we present a novel data miming approach to predict long term behavior of stock trend. Traditional techniques on stock trend prediction have shown their limitations when using time series algorithms or volatility modelling on price ...
Comments