NORMA eResearch @NCI Library

Enhancing Bitcoin Price Prediction: Integrating LSTM with Key Technical Indicators for Advanced Financial Forecasting

Fidan, Gokhan (2023) Enhancing Bitcoin Price Prediction: Integrating LSTM with Key Technical Indicators for Advanced Financial Forecasting. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
Preview
PDF (Master of Science)
Download (965kB) | Preview
[thumbnail of Configuration Manual]
Preview
PDF (Configuration Manual)
Download (881kB) | Preview

Abstract

This study examines how effectively Long Short-Term Memory (LSTM) models predict Bitcoin prices when combined with particular technical indicators like Super Trend, Kaufman's Adaptive Moving Average, Fibonacci's Weighted Moving Average, and Average True Range Trailing StopLoss. The increasing popularity of Bitcoin as a leading cryptocurrency and the demand for precise financial forecasting instruments in this unstable market are the motivations behind this research. The study uses LSTM networks to capture the intricate, nonlinear patterns present in Bitcoin price movements using a dataset from Yahoo Finance. How these specific technical indicators are included influences the precision of Bitcoin price forecasts is the main research question. Several metrics, including Mean Absolute Error, Mean Squared Error, and the Coefficient of Determination, are used to thoroughly assess the performance of the LSTM model through cross-validation. The results show that the LSTM model's predictive accuracy is improved when the chosen technical indicators are added, underscoring the importance of these indicators in describing market dynamics. By addressing a gap in the literature about the integration of these particular indicators with LSTM models for Bitcoin price prediction, this study advances the field. It establishes the framework for upcoming studies in sophisticated predictive modelling and automated trading systems and provides traders and investors in the cryptocurrency markets with insightful information. The study also emphasizes how crucial model interpretability and transparency are in the rapidly changing field of AI-driven financial analysis.

Item Type: Thesis (Masters)
Supervisors:
Name
Email
Rifai, Hicham
UNSPECIFIED
Subjects: H Social Sciences > HG Finance
Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence
Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence
H Social Sciences > HG Finance > Money > Digital currency
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Ciara O'Brien
Date Deposited: 08 May 2025 10:24
Last Modified: 08 May 2025 10:24
URI: https://norma.ncirl.ie/id/eprint/7511

Actions (login required)

View Item View Item