Cryptocurrency Price Prediction Using Ensemble Methods and Sentiment Analysis

Devireddy, Samara Simha Reddy (2024) Cryptocurrency Price Prediction Using Ensemble Methods and Sentiment Analysis. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (679kB) | Preview
Preview	PDF (Configuration Manual) Download (502kB) | Preview

Abstract

This study focuses on constructing the intersection of financial analytics and machine learning in predicting price movements of the world's most popular cryptocurrency, Bitcoin. In this effort of creating a robust predictive model that considers quantitative and qualitative measures, we will turn to historical price data and sentiment analysis from news headlines. Start with preprocessing the data to align the dates and fixing missing values. Then compute some indicators, such as Bollinger Bands, Relative Strength Index (RSI), Simple Moving Averages, and Exponential Moving Averages. Further, sentiment scores are extracted from relevant news feeds to quantify the market sentiment by using a model pre-trained, the so-called cryptobert. Random Forest, XGBoost, Long Short-Term Memory networks (LSTM) and finally, Auto Regressive Integrated Moving Average (ARIMA) were the four predictive models developed. All these models offer a rather unique insight into the pattern of price movements. These predictions were consolidated using an ensemble method, which aims to integrate the strength of each individual model. The results show that there is evidence machine learning can increase cryptocurrency price forecasts. Especially, the accuracy through this approach is way above that using an individual model. The importance of integrating market sentiment and traditional indicators in the previous study provides a step toward developing a framework of financial analytics for the future.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Niculescu, Hamilton UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science H Social Sciences > HG Finance > Money > Digital currency Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning H Social Sciences > HG Finance > Investment > Stock Exchange
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	15 Aug 2025 17:13
Last Modified:	15 Aug 2025 17:13
URI:	https://norma.ncirl.ie/id/eprint/8550

Actions (login required)

View Item