How arun-prasath-14/ai_loan_acceptance_and_analyze_risk works
Loan-IQ combines a React applicant-facing interface with a Flask credit-risk and bank-policy service. The primary workflow collects an application, requests an underwriting assessment, and presents the decision, policy checks, and SHAP rationale; users can then ask policy questions with assessment context. A separate policy-assistant workflow uses hybrid FAISS/BM25 retrieval and RRF reranking over bank and regulatory manuals. The README documents several backend capabilities not fully visible in the sampled excerpts, so those links are cited to the README; unsampled API routing is shown as unverified.
Main entry points: app.py Flask service · App.jsx Workspace router · api.js API client · EvaluationResultTab.jsx Decision and rationale
Components 18
Applicant interface
- Workspace router
src/App.jsx - Overview and glossary
src/components/OverviewTab.jsx - Application form
src/components/ApplicationFormTab.jsx - Decision and rationale
src/components/EvaluationResultTab.jsx - Policy chat
src/components/PolicyAssistantTab.jsx - API client
src/services/api.js
Credit assessment
- Sanity and hard rules
app.py - Risk scoring
app.py - Stacking model
models/loan_model.pkl - Feature preprocessing
models/preprocessor.pkl - SHAP explanation
app.py - Decision and recommendations
app.py
Policy intelligence
- Hybrid retrieval and RRF
app.py - Bank and RBI manuals
knowledge_base - FAISS and BM25 indexes
rag_index - Policy response synthesis
app.py
Application service
- Flask service
app.py
Other components
- Applicant
Connections 22
- Applicant → Workspace router: uses
README.md - Workspace router → Overview and glossary: renders
src/App.jsx - Workspace router → Application form: renders
src/App.jsx - Workspace router → Decision and rationale: renders
src/App.jsx - Workspace router → Policy chat: renders
src/App.jsx - Application form → API client: submits
src/components/ApplicationFormTab.jsx - API client → Flask service: requests assessment
- Policy chat → API client: sends query
src/components/PolicyAssistantTab.jsx - API client → Flask service: requests chat
- Flask service → Sanity and hard rules: runs checks
app.py - Flask service → Risk scoring: runs scoring
app.py - Risk scoring → Feature preprocessing: transforms features
README.md - Risk scoring → Stacking model: scores with
README.md - Flask service → SHAP explanation: generates rationale
README.md - Flask service → Decision and recommendations: combines assessment
README.md - Flask service → Hybrid retrieval and RRF: queries policies
README.md - Hybrid retrieval and RRF → FAISS and BM25 indexes: searches
README.md - Hybrid retrieval and RRF → Bank and RBI manuals: retrieves passages
README.md - Flask service → Policy response synthesis: synthesizes answer
app.py - Hybrid retrieval and RRF → Policy response synthesis: supplies context
app.py - Flask service → Decision and rationale: returns assessment
- Decision and rationale → Policy chat: starts follow-up
src/components/EvaluationResultTab.jsx