This project is a course assignment for the Data Mining course (COMP7103C) at HKU. The goal is to predict Bitcoin stock prices using Long Short-Term Memory (LSTM) neural networks. The project involves data collection, cleaning, exploratory data analysis, feature engineering, and model building.
Team: Yuxi CHEN (Dylan)
Source Code: bitcoin_price_prediction-lstm.ipynb
Dataset: BTC-USD.csv
The Bitcoin price dataset includes historical data points representing the price of Bitcoin. The dataset features include:
- Date: The date of the recorded Bitcoin price.
- Open: The price at the beginning of the trading day.
- Close: The price at the end of the trading day.
- Adj. Close: The adjusted close price accounting for corporate actions.
- High: The highest price during the trading day.
- Low: The lowest price during the trading day.
These features are used for financial analysis, prediction, and decision-making. By analyzing historical data, patterns and trends can be identified to predict future prices.
If you encounter any issues, you can view the results in bitcoin_price_prediction-lstm.html
or contact us
-
Clone the Project
git clone https://github.com/Dylan-CS/COMP7103_Bitcoin_Price_Prediction_LSTM.git
-
Open the Jupyter Notebook
Open
bitcoin_price_prediction-lstm.ipynb
in JupyterLab. -
Install Required Libraries
Ensure you have the necessary libraries installed. Run the following commands in your command line:
pip install pandas numpy matplotlib seaborn plotly scikit-learn tensorflow
-
Run the Jupyter Notebook
Execute the notebook to see the entire process:
- Import Libraries Needed for the data mining project
- Data Collection, Cleaning, and Preparation
- Exploratory Data Analysis & Feature Engineering
- Splitting the Time-series Data
- Scaling Data using Min-Max scaler
- Model Building
- Prediction & Analysis
jupyter nbconvert --to script bitcoin_price_prediction-lstm.ipynb; pipreqs .