Bitcoin technical trading with artificial neural network
Bitcoin technical trading with artificial neural network
复制标题
DOI：
10.1016/j.physa.2018.07.017
复制
发表时间：
2018-11-15
影响因子：
3.3
通讯作者：
Takahashi, Soichiro
中科院分区：
文献类型：
--
作者：
Nakano, Masafumi;Takahashi, Akihiko;Takahashi, Soichiro
本文探讨了基于人工神经网络进行收益预测的比特币日内技术交易。特别是，我们的深度学习方法成功地通过七层神经网络结构针对技术指标的给定输入数据发现交易信号，这些技术指标是根据过去的时间序列数据每 15 分钟计算一次。在可行的执行成本设置下，数值实验表明我们的方法显着提高了买入并持有策略的绩效。特别是，我们的模型在 2017 年 12 月至 2018 年 1 月的充满挑战的时期表现良好，在此期间比特币遭受了大幅负回报。此外，对层数、激活函数、输入数据和输出分类的变化进行了各种敏感性分析，以确认我们方法的稳健性。 (C) 2018 Elsevier B.V. 保留所有权利。
This paper explores Bitcoin intraday technical trading based on artificial neural networks for the return prediction. In particular, our deep learning method successfully discovers trading signals through a seven layered neural network structure for given input data of technical indicators, which are calculated by the past time-series data over every 15 min. Under feasible settings of execution costs, the numerical experiments demonstrate that our approach significantly improves the performance of a buy-and-hold strategy. Especially, our model performs well for a challenging period from December 2017 to January 2018, during which Bitcoin suffers from substantial minus returns. Furthermore, various sensitivity analysis is implemented for the change of the number of layers, activation functions, input data and output classification to confirm the robustness of our approach. (C) 2018 Elsevier B.V. All rights reserved.