https://github.com/vishalchau2003/wallet-credit-scoring
https://github.com/vishalchau2003/wallet-credit-scoring
Last synced: 3 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/vishalchau2003/wallet-credit-scoring
- Owner: Vishalchau2003
- Created: 2025-07-16T10:58:30.000Z (3 months ago)
- Default Branch: main
- Last Pushed: 2025-07-16T11:18:05.000Z (3 months ago)
- Last Synced: 2025-07-17T15:16:21.583Z (3 months ago)
- Language: Python
- Size: 109 KB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Wallet Credit Scoring — Aave V2 Protocol
## Problem Statement
We are required to develop a machine learning model that assigns a credit score between 0–1000 to each wallet based on transaction data from the Aave V2 protocol. The scoring reflects wallet behavior: higher scores represent safer, more reliable wallets, and lower scores reflect risky or exploitative behavior.
---
## Approach
### Features Engineered
- **Total deposits**: Indicates active participation.
- **Total borrows**: Higher borrow counts may indicate risk.
- **Total repays**: Reflects responsible behavior.
- **Total liquidation calls**: High risk, penalized in scoring.
### Scoring Logic
- **Base score**: 500 points.
- **+2 points** per deposit.
- **+5 points** per repay.
- **-1 point** per borrow.
- **-20 points** per liquidationcall.
- Score capped between **0 and 1000**.
---
## How to Run
1. **Install Dependencies:**
```bash
pip install pandas matplotlib