Skip to content

README.md

Latest commit

 

History

History
89 lines (64 loc) · 1.9 KB

README.md

File metadata and controls

89 lines (64 loc) · 1.9 KB

Trader Behavior & Market Sentiment Analysis

Overview

This project analyzes the relationship between Bitcoin market sentiment and trader behavior using historical trading data and the Fear & Greed Index.

The objective is to uncover how emotional market conditions influence trading activity, profitability, risk appetite, and overall trader performance.

Datasets Used

1. Bitcoin Fear & Greed Index

Contains:

  • Date
  • Market sentiment classification
    • Fear
    • Extreme Fear
    • Greed
    • Extreme Greed

2. Historical Trader Data

Contains:

  • Account information
  • Trade execution price
  • Trade size
  • Buy/Sell side
  • Closed PnL
  • Fees
  • Timestamps

Technologies Used

  • Python
  • Pandas
  • NumPy
  • Matplotlib
  • Seaborn
  • Jupyter Notebook

Project Workflow

  1. Data Cleaning
  2. Date Formatting
  3. Dataset Merging
  4. Exploratory Data Analysis (EDA)
  5. Visualization & Pattern Discovery
  6. Risk Analysis
  7. Insight Generation

Key Insights

  • Market sentiment strongly influenced trading activity and trader behavior.
  • Greed-driven periods showed higher participation and trading volume.
  • Trader profitability varied across emotional market conditions.
  • High-risk trading behavior increased during volatile market phases.
  • A small percentage of traders contributed disproportionately to total profitability.

Visualizations Included

  • Market Sentiment Distribution
  • Average PnL by Sentiment
  • Buy vs Sell Analysis
  • Trading Volume Analysis
  • Correlation Heatmap
  • Risk Category Distribution
  • Profitability by Risk Category
  • Top Trader Analysis

Conclusion

This analysis demonstrates that emotional market sentiment significantly impacts trader behavior, profitability, and risk-taking patterns in crypto markets.

The findings highlight the importance of sentiment-aware trading strategies and data-driven decision making in volatile financial environments.

Author

Bandita Sawant