GSoC 2026 Final Report - AI-Powered Loan Contract Analysis for the Mifos Ecosystem

A GSoC 2026 developer built an AI-powered loan contract analysis and summarization tool for the Mifos Initiative, part of the Apache Fineract ecosystem. The system extracts financial terms from loan contracts using large language models, validates data through a five-layer verification process, and generates plain-language summaries in English and Hindi. It supports five LLM providers, document upload with OCR, and direct integration with Mifos X, achieving 88–100% extraction accuracy.

This document is the final report for my GSoC 2026 project with the Mifos Initiative https://github.com/openMF part of the Apache Fineract ecosystem . My project focused on building an AI-Powered Loan Contract Analysis & Summarization Tool an intelligent system that uses Large Language Models to extract financial terms from loan contracts, validate data accuracy through multi-layer verification, and generate plain-language summaries that empower borrowers to make informed decisions. The project was built from scratch over 15 weeks 95 working days : a FastAPI + Python backend powering an AI analysis pipeline, a React 19 + Vite frontend, full Apache Fineract integration , support for 5 LLM providers including local inference via Ollama , and document upload with OCR all production-ready with Docker, CI/CD, and comprehensive testing. Note Accepted GSoC Proposal Reference If you'd like a concrete example of a strong proposal — structure, milestones, and approach: View my accepted GSoC 2026 proposal PDF » https://summerofcode.withgoogle.com/media/user/b45ca60ade54/proposal/gAAAAABqiY-IHyS3wb8po t6ek9Jv4JpYJtctTtaRIjgq6ZAmGIN uqACKRehGQPbO EnoJnn-elATeHtios2CansItUcaWO2bJf1sHUdmwnru-fHOPWi3Y=.pdf Tip All my contributions: Browse all commits by me » https://github.com/hopessugar/mifos-loan-summarizer/commits/main · View the full repository » https://github.com/hopessugar/mifos-loan-summarizer Project Overview -project-overview Project Timeline -project-timeline Architecture -architecture Phase 1 — AI Extraction & Analysis Pipeline -phase-1--ai-extraction--analysis-pipeline-weeks-15 Phase 2 — Apache Fineract Integration -phase-2--apache-fineract-integration-weeks-611 Phase 3 — Document Upload & OCR -phase-3--document-upload--ocr-weeks-1215 Demos -demos Technical Highlights -technical-highlights Key Metrics -key-metrics Challenges & Learnings -challenges--learnings Documentation -documentation Future Work -future-work Conclusion -conclusion Millions of borrowers worldwide especially in developing economies — sign loan agreements they don't fully understand. Complex legal language, hidden fees, predatory clauses, and language barriers prevent informed decision-making, driving financial exclusion and debt traps. An AI-powered system that takes a loan contract pasted text, uploaded PDF/DOCX, or pulled directly from Mifos X / Apache Fineract and delivers: | Capability | What it does | |---|---| 🔍 Smart Extraction | Extracts 20+ financial entities rates, fees, penalties, terms with 88–100% accuracy | ✅ 5-Layer Validation | Levenshtein matching, TF-IDF cosine similarity, numerical cross-check, EMI math verification, hallucination detection | ⚠️ Risk Scoring | 0–10 risk scale with predatory lending detection, borrower protection scoring, and negotiation tips | 📝 Plain-Language Summary | Clear, borrower-friendly summaries in English & Hindi | 💬 WhatsApp Export | Compact <300-char summary for easy mobile sharing | 🔌 Fineract Integration | Direct data pull from Mifos X — bypasses LLM extraction for 100% accurate structured data | 📄 Document Upload | PDF, DOCX, TXT, and image uploads with OCR Tesseract | 🤖 5 LLM Providers | Gemini, Groq, Ollama local , Cerebras, HuggingFace — with timeout-based automatic fallback | 15 Weeks · 95 Days · From Zero to Production-Ready AI System Core AI pipeline: extraction, validation, risk scoring, summarization, React frontend, CI/CD Built the entire AI analysis engine from scratch a multi-stage async pipeline that takes raw loan contract text and produces structured, validated financial data with confidence scores, risk analysis, and borrower-friendly summaries. | Area | What was built | |---|---| FastAPI Backend | REST API skeleton, routers, middleware CORS, logging, rate limiting , async request handling | Pydantic Schemas | LoanAgreementSchema with 20+ typed financial entity fields, request/response models | LLM Provider Registry | Pluggable provider system supporting Gemini, Groq, Ollama, Cerebras, HuggingFace with retry logic | Extraction Pipeline | Prompt engineering for structured JSON extraction, 3-tier extraction path Instructor / Native JSON / Raw , provider-aware routing | Contract Segmentation | 3 strategies header-based regex, NLTK sentence-based, TF-IDF semantic chunking — with adaptive selection | 5-Layer Validation | Levenshtein fuzzy matching 80% threshold , TF-IDF cosine similarity, numerical cross-check, EMI math verification Decimal -based , hallucination detection | Risk Analysis | 0–10 risk scoring, RBI-guideline-based thresholds, predatory lending detection, default clause classification standard vs. predatory | Financial Calculator | Reducing balance & flat rate EMI formulas, total cost calculation — all using Python Decimal for financial precision | Summarizer | LLM-powered plain-language summaries EN/HI , WhatsApp-ready <300-char export, language-aware provider routing | Input Sanitization | Prompt injection detection & prevention, delimiter-based prompt hardening | React Frontend | ContractInput , AnalysisView , EntityCard , RiskBadge , ExportButton , loading states, error boundaries | Testing | 95+ unit & integration tests, 85% coverage, security tests for prompt injection | CI/CD | GitHub Actions CI, CD, Security scanning — Bandit, Safety, npm audit, Trivy | Docker | Multi-stage Dockerfiles, docker-compose with health checks, production-ready config | 📋 Key Commits Phase 1 - click to expand | Commit | Description | |---|---| 1cd4940 | 6d51b63 78f5d5b c8ade26 72cd7e8 3a93b6a 7b796ad 697b4aa 39ab329 b68076e bdd1a65 Direct Mifos X integration, Ollama local LLM support, production hardening, comprehensive documentation Integrated the app directly with Apache Fineract / Mifos X. The key architectural insight: bypass LLM extraction entirely for Fineract products — build the LoanAgreementSchema directly from Fineract's structured JSON 100% accurate, no hallucination risk , and use the LLM only for human-readable summary generation. Also built a complete Ollama integration 325-line native provider using Ollama's HTTP API directly — enabling fully local, offline, privacy-preserving loan analysis. | Area | What was built | |---|---| Fineract Service | fineract service.py 711 lines — async HTTP client with connection pooling, caching 5-min TTL , retry logic tenacity , SSL config 3 modes , Basic Auth + tenant headers | Direct Schema Builder | build schema from fineract — maps every Fineract field to LoanAgreementSchema directly from JSON. Interest rate normalization per-period → annual , charge classification 7 fee categories , down payment handling, grace periods, multi-disbursement support | Charge Classification | Maps Fineract charge arrays to specific fee fields using chargeTimeType + name-based classification: processing, late, prepayment, insurance, admin, other — with percentage vs. flat distinction | API Endpoints | GET /loanproducts cached list , GET /loanproducts/{id} product detail , POST /loanproducts/refresh cache invalidation , enhanced /health with Fineract connectivity status | Currency Utilities | 50+ ISO 4217 currency codes → display symbols, format currency and format currency precise — multi-currency support INR, USD, KES, etc. | Ollama Provider | 325-line native provider generate native streaming text , generate json Ollama JSON mode , auto-model-pull, health check, 120s timeout for local inference | Loan Simulator | /simulator endpoint full amortization schedule with month-by-month EMI breakdown, flat/reducing rate support, Decimal precision | Frontend | MifosProductPicker component auto-fetch products, loading/error/retry states, refresh button, product count, graceful Fineract-down fallback | Testing | test fineract service.py 444 lines + test integration fineract.py 416 lines — 19 test classes covering SSL, auth, API, caching, health check | Documentation | CONTRIBUTING.md 550 lines , DOCKER SETUP.md 693 lines , LLM PROVIDER COMPARISON.md 531 lines , LOCAL MODEL SETUP GUIDE.md 1,029 lines | 📋 Key Commits Phase 2 — click to expand | Commit | Description | |---|---| c17e72a | bdcc3f6 d0d0236 999b01e e20c2cd 2274ba0 c1bb952 75de5a5 2237504 PDF/DOCX/image upload, Tesseract OCR, frontend polish Built a complete document processing pipeline — users can upload loan agreements as files PDF, DOCX, TXT, or images and the system automatically extracts the text with OCR for scanned documents before feeding it through the existing AI analysis pipeline. Also wrote 4 comprehensive documentation guides totaling 2,800+ lines. | Area | What was built | |---|---| PDF Service | pdf service.py 473 lines — PyMuPDF text extraction, Tesseract OCR fallback per-page, 300 DPI , DOCX paragraphs + tables , TXT multi-encoding fallback chain , image OCR PNG/JPG | Text Cleanup | clean extracted text — null byte stripping, form feed → newline, hyphenated line-break repair agree-\nment → agreement , whitespace normalization | File Validation | Extension check, 10MB size limit, empty file detection, encrypted PDF detection, .doc vs .docx format guidance | API Endpoint | POST /analyze/pdf — multipart/form-data , UploadFile , rate-limited 10/min , specific error messages per failure mode | React Component | PdfUpload 318 lines — drag-and-drop zone with visual feedback, file type badges color-coded by format , size display, upload progress bar, loading/error states | Frontend Integration | Tab-based input switching paste / upload / Fineract , analyzeFile hook, proper state cleanup on tab switch | Clipboard Paste | Image paste from clipboard via Clipboard API → OCR → analysis | Docker OCR | tesseract-ocr + tesseract-ocr-hin installed in backend container for out-of-box OCR support | 📋 Key Commits Phase 3 — click to expand | Commit | Description | |---|---| b68076e | Paste a loan contract → AI extracts 20+ entities → 5-layer validation → risk score → plain-language summary Select a loan product from Mifos X → schema built directly from Fineract JSON no LLM extraction → validated → summarized Upload a PDF/DOCX/image → text extracted with OCR for scanned docs → full AI analysis pipeline The most impactful architectural decision was creating two separate analysis paths : Path A: Text/PDF → LLM Extraction → Validation → Summary user-uploaded contracts Path B: Fineract → Direct JSON Map → Validation → Summary Mifos X products Path B bypasses LLM extraction entirely every value comes from Fineract's authoritative API. The LLM is used only for summary generation the one thing it excels at . This gives 100% data accuracy with 2–3× faster response times. After a brutal debugging session Day 34 where floating-point arithmetic turned Rs. 8,885 into 8884.999999999998 , the entire financial calculation layer was rewritten to use Python's Decimal module. Rule: never use float for money. This is non-negotiable for financial applications. Instead of fighting instructor compatibility, I built a native Ollama provider using Ollama's HTTP API directly: Streaming generation via httpx.stream no timeouts on slow hardware JSON mode format: "json" for 95%+ parse success rate vs. ~70% with prompt-based JSON Auto-model-pull on first run set OLLAMA MODEL=llama3.2:latest and the app handles the rest Detailed health check reports running status, model availability, installed models The risk analysis system distinguishes between standard default triggers "miss 3 payments" and predatory ones "at lender's sole discretion" . Only predatory clauses increase the risk score. Fineract's flat charge array is automatically classified into 7 fee categories using a combination of chargeTimeType codes and name-based pattern matching with percentage vs. flat distinction for each: disbursement time → processing fee overdue time → late fee flat / late payment interest % name: prepayment → prepayment penalty name: insurance → insurance fee name: admin → administrative fee everything else → other fee | | | Layer | Technologies | |---|---| Backend | Python 3.11, FastAPI, Pydantic v2, httpx async , Tenacity retry | AI/ML | LangChain, Instructor, NLTK, scikit-learn TF-IDF , tiktoken | LLM Providers | Google Gemini, Groq, Ollama local , Cerebras, HuggingFace Inference | Document Processing | PyMuPDF, python-docx, Tesseract OCR, Pillow | Frontend | React 19, Vite, Tailwind CSS, Axios, i18n | Infrastructure | Docker multi-stage , docker-compose, Nginx, GitHub Actions | Security | Bandit, Safety, Trivy, npm audit, API key auth, input sanitization | Testing | pytest, pytest-asyncio, pytest-cov, unittest.mock | | | Challenge | What went wrong | What I learned | |---|---|---|---| | 1 | Floating-point precision | float math turned 8885 into 8884.999999999998 . EMI validation flagged correct values as wrong. | Never use Python's float for money. Decimal module exists for a reason. Rewrote the entire financial calculator. | | 2 | Async event loop blocking | Sync LLM API calls froze FastAPI — the whole app hung on concurrent requests. | asyncio.to thread wraps sync calls to play nice with async. Now handles 10+ concurrent requests. | | 3 | Prompt engineering | First prompts returned paragraphs of explanation instead of JSON. LLMs confused "late fee" with "late payment interest." | Be painfully explicit: "Return ONLY valid JSON." Include the schema in the prompt. Add disambiguation instructions. Took ~10 iterations to get 85%+ accuracy. | | 4 | Ollama + Instructor | The instructor library works with OpenAI-compatible APIs but breaks with Ollama's quirks. 5–10 seconds wasted per request on failed attempts. | Built a native Ollama provider using the HTTP API directly. Ollama's format: "json" mode is far more reliable than prompt-based JSON. | | 5 | Docker networking | Containers couldn't communicate. Ollama on host unreachable from Docker backend localhost resolves to the container, not the host . | host.docker.internal resolves to the host machine. Set up Docker early — not in Week 5 when the project is complex. | Daily stand-ups with mentor learned to communicate blockers early instead of debugging alone for hours PR discipline conventional commits, clear descriptions, linking to issues Documentation as a first-class deliverable 4 comprehensive guides totaling 2,800+ lines | Document | Lines | Description | |---|---|---| README.md | CONTRIBUTING.md DOCKER SETUP.md LLM PROVIDER COMPARISON.md LOCAL MODEL SETUP GUIDE.md GSoC Daily Work Log.md These are areas I'd love to see the project grow into: | Area | Description | |---|---| Batch Processing | Analyze multiple contracts at once for MFIs processing loan portfolios | More Languages | Expand to other language for global MFI coverage | Fine-Tuned Models | Train a domain-specific model for higher extraction accuracy | Mobile App | React Native or KMP client for field officers to scan contracts on-the-go | Regulatory Compliance | Auto-check against country-specific lending regulations RBI, CFPB, etc. | Borrower Dashboard | Track multiple loans, compare offers, monitor risk over time | Webhook Notifications | Alert MFI admins when a high-risk loan product is detected | This summer, I built a production-ready AI system from scratch from the first git init to a deployed Docker application with 120+ tests, 5 LLM providers, Apache Fineract integration, OCR-powered document processing, and comprehensive documentation. On the technical side , I learned to ship real software: async Python at scale, LLM reliability engineering prompt iteration, structured output, fallback chains , financial precision Decimal , not float , multi-provider architecture, and the discipline of CI/CD and security scanning from Day 1. On the human side , I learned to work in the open: daily stand-ups, clear commit messages, scope negotiation, and writing documentation that helps the next contributor. I kept a 95-day engineering diary https://github.com/hopessugar/mifos-loan-summarizer/blob/main/GSoC Daily Work Log.md that documents every decision, failure, and lesson including the ones I'm not proud of. The project matters because financial literacy shouldn't require a law degree . If this tool helps even one borrower spot a predatory clause or understand the true cost of their loan, it was worth building. Huge thanks to: Akshat Sharma and Rahul Goel for fast feedback loops, honest design reviews, and the patience to say "start simple" when I was overengineeringfor building the infrastructure that makes financial inclusion possible Mifos Initiative https://mifos.org/ for the opportunity, structure, and funding that made this work possible Google Summer of Code https://summerofcode.withgoogle.com/ the core banking platform this tool integrates with Apache Fineract https://fineract.apache.org/ - The open-source LLM ecosystem Gemini, Groq, Ollama, and the communities behind them Built with ❤️ during GSoC 2026 🔗 Repository https://github.com/hopessugar/mifos-loan-summarizer · 📋 Daily Work Log https://github.com/hopessugar/mifos-loan-summarizer/blob/main/GSoC Daily Work Log.md · 📚 API Docs https://github.com/hopessugar/mifos-loan-summarizer/blob/main/README.md -documentation · 📄 GSoC Proposal https://summerofcode.withgoogle.com/media/user/b45ca60ade54/proposal/gAAAAABqiY-IHyS3wb8po t6ek9Jv4JpYJtctTtaRIjgq6ZAmGIN uqACKRehGQPbO EnoJnn-elATeHtios2CansItUcaWO2bJf1sHUdmwnru-fHOPWi3Y=.pdf