Bitcoin Price Forecasting: Linear Discriminant Analysis with Sentiment Evaluation

doi:10.1145/3485557.3485561

Paper

Bitcoin Price Forecasting: Linear Discriminant Analysis with Sentiment Evaluation

Published Aug 25, 2021 · Ikhlaas Gurrib, Firuz Kamalov, Linda Smail

The 7th Annual International Conference on Arab Women in Computing in Conjunction with the 2nd Forum of Women in Research

UNKNOWN SJR score

5

Citations

0

Influential Citations

Full text

Semantic Scholar

Abstract

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.

Study Snapshot

Key takeawayThe proposed method using linear discriminant analysis and sentiment analysis effectively predicts bitcoin price direction, with a forecast accuracy of 0.828 and AUC of 0.840 on test data.

PopulationOlder adults (50-71 years)

Sample size24

MethodsObservational

OutcomesBody Mass Index projections

ResultsSocial networks mitigate obesity in older groups.

Sign up to use Study Snapshot

Consensus is limited without an account. Create an account or sign in to get more searches and use the Study Snapshot.

Create an account

Paper

Bitcoin Price Forecasting: Linear Discriminant Analysis with Sentiment Evaluation

Sign up to use Study Snapshot

References

Financial Forecasting with Machine Learning: Price Vs Return

Stock price is a more effective input feature than return value in predicting the direction of stock price movement using machine learning models.

Forecasting with Deep Learning: S&P 500 index

Our convolution-based neural network model accurately predicts the future value of the S&P 500 index with over 55% accuracy, outperforming various benchmarks.

Forecasting Bitcoin Price Fluctuation by Twitter Sentiment Analysis

Twitter sentiment analysis can accurately predict Bitcoin price fluctuations with 62.48% accuracy.

Forecasting the price of Bitcoin using deep learning

The SDAE deep learning method outperforms other popular machine learning methods in predicting Bitcoin's price, providing better directional and level predictions.

Predicting next day direction of stock price movement using machine learning methods with persistent homology: Evidence from Kuala Lumpur Stock Exchange

Combining machine learning methods with persistent homology improves the prediction of stock price movements, with support vector machine being the best performer.

Citations

Comprehensive analysis of machine learning models for predicting concrete compressive strength

Ensemble models like stacking and gradient boost provide superior accuracy in predicting concrete compressive strength, but are significantly slower than linear models.

Machine learning methods in civil engineering: a systematic review

Machine learning has potential applications in civil engineering, but also poses risks, and this paper reviews recent developments in AI for insights.

Twitter Attribute Classification With Q-Learning on Bitcoin Price Prediction

Our classification of tweet attributes, based on follower count, leads to 80% less time, 88.8% less CPU consumption, and 12.5% more accurate Bitcoin price predictions compared to the classic approach.

Predicting Key Predictors of Project Desertion in Blockchain: Experts’ Verification Using One-Sample T-Test

12 key predictors of Blockchain project desertion were identified, which can help identify developers who may abandon projects and guide future research efforts.