This project analyzes how market sentiment (Fear vs Greed) influences trader behavior and profitability in the Bitcoin market.
By combining the Bitcoin Fear & Greed Index with historical trading data, the project uncovers patterns in trading volume, leverage usage, and profit/loss under different sentiment conditions.
The goal is to understand whether emotional market phases affect trading decisions and outcomes.
-
Bitcoin Fear & Greed Index
- Daily sentiment classification (Fear / Greed)
- Numerical sentiment score
-
Historical Trader Data
- Trade execution details
- Profit & Loss (PnL)
- Trade size and leverage
- Timestamps
- Python
- Pandas
- NumPy
- Matplotlib
- Seaborn
- Jupyter Notebook
- Data loading and inspection
- Data cleaning and preprocessing
- Sentiment encoding (Fear = 0, Greed = 1)
- Dataset merging based on date
- Exploratory Data Analysis (EDA)
- Visualization of trading patterns
- Insight generation
- Greed phases show higher average profitability.
- Fear phases are associated with more loss-making trades.
- Trade volume and activity increase during Greed periods.
- Traders tend to take more aggressive positions when market sentiment is positive.
- Profit/Loss comparison by sentiment
- Trade volume distribution
- Sentiment-wise trading behavior
- Trend analysis over time
Understanding trader psychology is crucial in financial markets.
This project demonstrates how sentiment-driven analysis can support:
- Risk management
- Strategy optimization
- Market behavior prediction
- Add statistical significance testing
- Include volatility analysis
- Build an interactive dashboard (Streamlit / Power BI)
- Extend analysis to other cryptocurrencies
Eldho Joshy
Aspiring Data Scientist