https://github.com/quantdevjayson/robo-credit-underwriter-multi-rl

AI-driven credit underwriting system combining Machine Learning (ML) & Reinforcement Learning (RL) to optimize loan approvals while managing risk: Credit Risk Prediction via Random Forest model; PPO & DQN for dynamic risk control; Custom OpenAI Gym Environment for simulating real-world lending scenarios & FastAPI real-time processing.
https://github.com/quantdevjayson/robo-credit-underwriter-multi-rl

ai-driven-chatbot credit-risk cvar-optimization deep-q-learning fastapi ppo-agent reinforcement-learning-agent risk-underwriting robotics-simulation streamlit-webapp synthetic-data

Last synced: 8 months ago
JSON representation

AI-driven credit underwriting system combining Machine Learning (ML) & Reinforcement Learning (RL) to optimize loan approvals while managing risk: Credit Risk Prediction via Random Forest model; PPO & DQN for dynamic risk control; Custom OpenAI Gym Environment for simulating real-world lending scenarios & FastAPI real-time processing.

• Host: GitHub
• URL: https://github.com/quantdevjayson/robo-credit-underwriter-multi-rl
• Owner: QuantDevJayson
• License: mit
• Created: 2025-02-20T00:54:55.000Z (8 months ago)
• Default Branch: main
• Last Pushed: 2025-02-20T01:23:22.000Z (8 months ago)
• Last Synced: 2025-02-20T01:37:26.950Z (8 months ago)
• Topics: ai-driven-chatbot, credit-risk, cvar-optimization, deep-q-learning, fastapi, ppo-agent, reinforcement-learning-agent, risk-underwriting, robotics-simulation, streamlit-webapp, synthetic-data
• Language: Jupyter Notebook
• Homepage:
• Size: 0 Bytes
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# robo-credit-underwriter-multi-rl

### Optimized AI Robo-Credit Underwriter with Multi-Agent RL & Risk-Aware Learning

**Outline:** 


This project implements an AI-powered credit underwriting system that leverages machine learning (ML) and reinforcement learning (RL) to optimize loan approval decisions while managing risk. It includes:


(i) ML-Based Credit Risk Prediction (Random Forest)


(ii) Reinforcement Learning Agents (PPO & DQN) for dynamic decision-making


(iii) FastAPI Server for real-time loan application processing


(iv) Risk-Aware Decision Model for enhanced financial risk management


#### Model Training Details 

**a) ML Model (Credit Scoring)** 


- Algorithm: Random Forest


- Features Used: Credit Score, Income, Debt-to-Income Ratio, Age, Employment Years, Loan Amount


- Output: Approval Decision (1 = Approved, 0 = Rejected)


**b) Reinforcement Learning Agents** 


- PPO (Proximal Policy Optimization) → Focuses on optimizing long-term rewards


- DQN (Deep Q-Networks) → Handles risk control in loan approvals


- Custom OpenAI Gym Environment simulates credit applications


**c) Risk-Aware Decision Policy** 


- Combines ML & RL to make more informed approval decisions


- Incorporates Risk Factors such as loan amount & interest rates


- Prevents High-Risk Lending through reinforcement learning penalties


#### Running the FastAPI Server

After training the models, start the API:  uvicorn api:app --reload

**Future Enhancements** 


✅ Expand dataset with real-world financial data 


✅ Improve model interpretability with SHAP values


✅ Deploy on AWS/GCP with real-time transaction processing


----------------------------------------------------------------------------

**Tech Stack:**

- *ML*: Scikit-Learn (Random Forest)


- *RL*: Stable-Baselines3 (PPO, DQN)


- *API*: FastAPI


- *Backtesting & Simulation*: OpenAI Gym


----------------------------------------------------------------------------

🚀 Ready to transform credit underwriting with AI? Let's go! 🎯