An automated cryptocurrency trading system based on the detection of unusual price movements with a Time-Series Clustering-Based approach
作者：
Highlights：
• We propose an end-to-end automated cryptocurrency trading system.
• We detect and remove the periods with unusual price movements.
• We use various classification algorithms for the prediction of price direction.
• The outlier detection step significantly increases return on investment.
• During the highly volatile periods the trading system becomes more profitable.
摘要
•We propose an end-to-end automated cryptocurrency trading system.•We detect and remove the periods with unusual price movements.•We use various classification algorithms for the prediction of price direction.•The outlier detection step significantly increases return on investment.•During the highly volatile periods the trading system becomes more profitable.
论文关键词：Price prediction,Dynamic time warping,Hierarchical clustering,Anomaly detection,Outlier detection,Machine learning
论文评审过程：Received 21 December 2021, Revised 18 February 2022, Accepted 27 March 2022, Available online 2 April 2022, Version of Record 4 April 2022.
论文官网地址：https://doi.org/10.1016/j.eswa.2022.117017
