Spaces:
Sleeping
Sleeping
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,19 +1,59 @@
|
|
| 1 |
---
|
| 2 |
title: ECL Risk Analyzer
|
| 3 |
-
emoji:
|
| 4 |
colorFrom: red
|
| 5 |
colorTo: red
|
| 6 |
sdk: docker
|
| 7 |
app_port: 8501
|
| 8 |
tags:
|
| 9 |
- streamlit
|
|
|
|
|
|
|
|
|
|
| 10 |
pinned: false
|
| 11 |
-
short_description: Streamlit
|
| 12 |
---
|
| 13 |
|
| 14 |
-
#
|
| 15 |
|
| 16 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
|
| 18 |
-
If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
|
| 19 |
-
forums](https://discuss.streamlit.io).
|
|
|
|
| 1 |
---
|
| 2 |
title: ECL Risk Analyzer
|
| 3 |
+
emoji: 💹
|
| 4 |
colorFrom: red
|
| 5 |
colorTo: red
|
| 6 |
sdk: docker
|
| 7 |
app_port: 8501
|
| 8 |
tags:
|
| 9 |
- streamlit
|
| 10 |
+
- credit-risk
|
| 11 |
+
- gemini
|
| 12 |
+
- finance
|
| 13 |
pinned: false
|
| 14 |
+
short_description: AI ECL analyzer using Streamlit and Gemini.
|
| 15 |
---
|
| 16 |
|
| 17 |
+
# 🧮 ECL Risk Analyzer
|
| 18 |
|
| 19 |
+
**ECL Risk Analyzer** is a Streamlit-based web app that automates **Expected Credit Loss (ECL)** analysis and provides **AI-driven recommendations** on credit decisions.
|
| 20 |
+
|
| 21 |
+
### 🔍 Features
|
| 22 |
+
- Upload loan datasets (CSV format).
|
| 23 |
+
- Compute key credit metrics:
|
| 24 |
+
- **PD** – Probability of Default
|
| 25 |
+
- **LGD** – Loss Given Default
|
| 26 |
+
- **EAD** – Exposure at Default
|
| 27 |
+
- **ECL** – Expected Credit Loss
|
| 28 |
+
- Visualize segment-level performance with interactive charts.
|
| 29 |
+
- Get AI recommendations (via **Gemini 2.5 Flash Lite**) to:
|
| 30 |
+
- Increase interest
|
| 31 |
+
- Reduce disbursement
|
| 32 |
+
- Maintain current policy
|
| 33 |
+
- Role-based access:
|
| 34 |
+
- **Analyst:** Run and review segment analyses.
|
| 35 |
+
- **CRO:** Audit all analyst reports and view trends.
|
| 36 |
+
|
| 37 |
+
### 🧠 Tech Stack
|
| 38 |
+
- **Frontend:** Streamlit
|
| 39 |
+
- **AI Engine:** Gemini API
|
| 40 |
+
- **Database:** SQLite (via SQLAlchemy)
|
| 41 |
+
- **Hosting:** Hugging Face Spaces (Docker SDK)
|
| 42 |
+
|
| 43 |
+
### 🚀 Quick Start
|
| 44 |
+
1. Upload your loan dataset (CSV).
|
| 45 |
+
2. Select a segmentation column (e.g., loan intent, area, or occupation).
|
| 46 |
+
3. View computed ECL metrics and charts.
|
| 47 |
+
4. Choose a segment to get AI-based recommendations.
|
| 48 |
+
|
| 49 |
+
### 📊 Example Output
|
| 50 |
+
| Segment | PD | LGD | EAD | ECL | Action |
|
| 51 |
+
|----------|----|-----|-----|-----|--------|
|
| 52 |
+
| Medical | 0.278 | 0.255 | 78M | 5.5M | Increase Interest |
|
| 53 |
+
|
| 54 |
+
### 🛠️ Customization
|
| 55 |
+
Modify `/src/streamlit_app.py` to:
|
| 56 |
+
- Adjust prompts or logic.
|
| 57 |
+
- Change chart styles.
|
| 58 |
+
- Extend user roles or security.
|
| 59 |
|
|
|
|
|
|