Sentiment Analysis on Cryptocurrency using Machine Learning and NLP
SUPERVISOR: LIU QI
Group: Ezen CHONG, Gillian Ru Qu TOO, Keith Kai Xuan CHAN, Zi Zheng FONG HU
PROJECT INTRODUCTION
Can new AI models be used to predict Cryptocurrency Market movements?
This project aims to leverage Natural Language Processing (NLP) and Machine Learning (ML) to analyze and predict cryptocurrency market trends based on sentiment analysis. The motivation behind this initiative is the significant impact of market sentiment, as reflected in news articles and social media, on the volatility of cryptocurrencies.
WHAT WE ARE DOING
Current Progress
Data Preprocessing
November 2024
- Initiate data collection
- Utilize open-sourced models like LLAMA
- import models locally via techniques such as QLORA
Machine Learning Model Training
January 2025
- Train ML models (Logistic Regression, SVM) for sentiment classification
- Develop sentiment indices for cryptocurrencies
- Develop predictive models for price movements and evaluate model performance
Refinement and Optimization
March 2025
- Optimize models based on evaluation results
- Perform extensive back testing with a larger dataset
- Analyze model robustness and reliability