This project focuses on analyzing Bitcoin's price cycles from 2010 to 2024. The objective is to break down Bitcoin's market movements into recognizable phases: Bear, Pre-Bull, 1st Bull, and 2nd Bull. Additionally, we apply machine learning (Random Forest Regressor) to predict future Bitcoin prices, focusing on 2025 as a year of potential significance in Bitcoin’s market cycle. The project includes visualizations, insights, and predictive modeling to explore the volatility and patterns within the Bitcoin market.
- Insight and Story.pdf: Contains detailed insights and the storyline of the data, including phase analyses and predictions.
- Dataset.csv: Historical Bitcoin price data from July 17, 2010, to September 14, 2024. Each entry includes the open, close, high, and low prices for each day.
- Notebook.ipynb: Jupyter Notebook that visualizes Bitcoin price charts, implements Random Forest Regressor for predicting future prices, and evaluates patterns within the dataset.
- requirements.txt: easy install python depedencies by runing the file.
- Cloning Repository: Clone this repository to your local machine with the command:
git clone https://github.com/fadhiljr7/datascience000.git - Install dependencies: Ensure you have Python and Jupyter installed. You can install the required libraries by running:
pip install -r requirements.txt - Explore the dataset and analysis by Open the Jupyter Notebook Notebook.ipynb using Jupyter:
jupyter notebook Notebook.ipynb - Go through the Insight and Story.pdf for a detailed explanation of Bitcoin’s historical price cycles, analysis on phase transitions, and differences with other models like Rekt Capital.
- Python: For data manipulation, analysis, and visualization.
- Jupyter Notebook: For interactive code execution and visualizations.
- Pandas: To handle and process the Bitcoin price dataset.
- Matplotlib: For creating the Bitcoin price charts.
- Scikit-learn: For implementing the Random Forest Regressor to predict future Bitcoin prices.
- Random Forest Regressor: The machine learning algorithm used to predict the potential highest price of Bitcoin in 2025.
This project offers a comprehensive analysis of Bitcoin's historical price cycles and explores future price predictions using machine learning. The insights drawn from this analysis could provide a better understanding of Bitcoin’s market behavior and assist in future investment decisions. The project highlights how Bitcoin's price moves through identifiable phases, and it explores the potential for future growth, with predictions focusing on 2025.