Cryptocurrency Quantitative Trading Strategy Based On Machine Learning Approach

This thesis adopts the LSTM model to predict the price trends of cryptocurrencies by combining their historical prices with various technical indicators as features for research. We designed six control experiments to compare the impact of different technical indicators as features on the model. The...

Full description

Bibliographic Details
Main Author: Fu, Dingyu
Format: Thesis
Language:English
Published: 2025
Subjects:
Online Access:http://eprints.usm.my/63845/
Abstract Abstract here
Description
Summary:This thesis adopts the LSTM model to predict the price trends of cryptocurrencies by combining their historical prices with various technical indicators as features for research. We designed six control experiments to compare the impact of different technical indicators as features on the model. The final results indicate that the LSTM model combined with technical indicators can effectively improve prediction accuracy, but not all technical indicators contribute to the improvement of the model.