Bitcoin price prediction using ensembles of neural networks
Authors:
- 1 July 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 666-671
Abstract
This paper explores the relationship between the features of Bitcoin and the next day change in the price of Bitcoin using an Artificial Neural Network ensemble approach called Genetic Algorithm based Selective Neural Network Ensemble, constructed using Multi-Layered Perceptron as the base model for each of the neural network in the ensemble. To better understand the practicality and its effectiveness in real-world application, the ensemble was used to predict the next day direction of the price of Bitcoin given a set of approximately 200 features of the cryptocurrency over a span of 2 years. Over a span of 50 days, a trading strategy based on the ensemble was compared against a “previous day trend following” trading strategy through back-testing. The former trading strategy generated almost 85% returns, outperforming the “previous day trend following” trading strategy which produced an approximate 38% returns and a trading strategy that follows the single, best MLP model in the ensemble that generated approximately 53% in returns.Keywords
This publication has 38 references indexed in Scilit:
- Analysis of Artificial Neural Network for Financial Time Series ForecastingInternational Journal of Computer Applications, 2010
- Ensemble-based classifiersArtificial Intelligence Review, 2009
- Neural networks and statistical techniques: A review of applicationsExpert Systems with Applications, 2009
- Evolving feature selectionIEEE Intelligent Systems, 2005
- Neural network ensemble strategies for financial decision applicationsComputers & Operations Research, 2005
- Hybrid genetic algorithms for feature selectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2004
- Data dimensionality reduction with application to simplifying rbf network structure and improving classification performanceIEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2003
- A dynamically generated fuzzy neural network and its application to torsional vibration control of tandem cold rolling mill spindlesEngineering Applications of Artificial Intelligence, 2002
- Ensembling neural networks: Many could be better than allArtificial Intelligence, 2002
- ANFIS: adaptive-network-based fuzzy inference systemIEEE Transactions on Systems, Man, and Cybernetics, 1993