Bitcoin price forecasting: Linear discriminant analysis with sentiment evaluation
Association for Computing Machinery
Cryptocurrencies such as bitcoin have garnered a lot of attention in recent months due to their meteoric rise. In this paper, we propose a new method for predicting the direction of bitcoin price using linear discriminant analysis (LDA) together with sentiment analysis. Concretely, we train an LDA-based classifier that uses the current bitcoin price information and Twitter headline news in order to forecast the next-day direction of bitcoin price. The proposed model achieves highly accurate results beating several benchmark targets. In particular, the proposed approach produces forecast accuracy of 0.828 and AUC of 0.840 on the test data. © 2021 Association for Computing Machinery. All rights reserved.
This conference paper is not available at CUD collection. The version of scholarly record of this article is published in ACM International Conference Proceeding Series (2021), available online at: https://doi-org.ezp.cud.ac.ae/10.1145/3485557.3485561
Bitcoin, Forecasting, Linear discriminant analysis, Natural language processing, Sentiment analysis
Gurrib, I., Kamalov, F., & Smail, L. (2021). Bitcoin price forecasting: Linear discriminant analysis with sentiment evaluation. Paper presented at the ACM International Conference Proceeding Series, 4, 1-5. https://doi-org.ezp.cud.ac.ae/10.1145/3485557.3485561