Automated Tradings System For Cryptocurrencies Using Amazon Cloud Computing

Abstract

This study analyzed the performance of three different models: Autoregressive Integrated Moving Average, Support Vector Machine, and Artificial Neural Network. The study utilized three performance metrics: Mean Absolute Error, Mean Squared Error, and Mean Absolute Percentage Error. The research methodology included training and testing the models on data sets with varying time frames. Results showed that the Artificial Neural Network model outperformed the Support Vector Machine and Autoregressive Integrated Moving Average models in the long term, while the Support Vector Machine model had better performance in the short term. However, the Autoregressive Integrated Moving Average model had the poorest performance among the three models. The study has important implications for the development of automated trading systems and can inform decision-making in the financial industry. Future research could explore new machine learning techniques and incorporate additional data sources to improve the accuracy of automated trading systems.