📈 Personal Finance Investment Strategist
Agentic Demo Showcase – Track 3 Entry
Agent-Based Financial Advisor Using LlamaIndex, Nebius AI, and Economic Data
Built by: [Devavrat Samak]
Tech Stack: LlamaIndex | meta-llama/Meta-Llama-3.1-70B-Instruct-fast (Nebius) | Modal Labs | Gradio | World Bank & Yahoo Finance APIs
Hackathon Track
This submission is for: Track 3: Agentic Demo Showcase agent-demo-track We use a multi-agent system to:
- Analyze user financial profile
- Enrich with demographic insights
- Fetch live economic indicators
- Generate personalized investment strategy
🔍 Overview
This agentic system provides intelligent, context-aware investment strategies based on:
| Feature | Description |
|---|---|
| User Profile | Age group, income, expenses, risk tolerance, goal, timeframe |
| Demographic Insights | Life stage, liquidity needs, planning horizon |
| Economic Analysis | Inflation, interest rates, GDP growth, market trends |
| Tax Awareness | Country-specific tax rules from India and G7 countries, i.e. USA, UK, Canada, Germany, France, Italy, Japan |
| Strategy Generation | Asset allocation, recommended instruments, monthly savings plan |
How It Works: The Agentic Framework
Agent Flow
Each agent uses natural language reasoning and external tools to build the final strategy.
Agents
| Agent | Role |
|---|---|
| Input Analyzer | Parses free-form input into structured profile |
| Demographic Profiler | Maps life stage, liquidity needs, planning horizon |
| Net Worth Checker | Identifies existing investments and assets |
| Financial Literacy Detector | Determines complexity level of advice |
| Economic Analyst | Gathers inflation, interest rate, GDP, and market trend |
| Strategy Advisor | Generates final investment plan |
Technical Architecture
Core Components
| Component | Purpose |
|---|---|
| LlamaIndex | Manages agent orchestration and reasoning flow |
| Qwen3-32B on Nebius | Generates human-readable investment strategy |
| World Bank API | Provides inflation and GDP data |
| Yahoo Finance | Detects market trend (bullish/bearish) |
| Hardcoded Interest Rates | For major countries (USA, India, UK, etc.) |
| Country Tax DB | Applies local tax logic to optimize portfolio |
| Modal Labs | Hosts backend as ASGI endpoint |
| Gradio | Frontend interface on Hugging Face Spaces |
Features
| Feature | Status |
|---|---|
| ✅ Multi-Agent Workflow | LlamaIndex-based |
| ✅ Country Support | India, USA, UK, Canada, Germany, France, Italy, Japan |
| ✅ Economic Indicators | Inflation, Interest Rate, GDP Growth, Market Trend |
| ✅ Tax-Aware Advice | Yes – country-specific |
| ✅ Risk Tolerance Mapping | Conservative / Moderate / Aggressive |
| ✅ Markdown Strategy Output | Clean, formatted response |
📹 Video Walkthrough
🎬 [Insert your video link here explaining how the agents work together]
Credits
Built with ❤️ by [Devavrat Samak]
For Hugging Face Gradio Hackathon 2025 – Track 3: Agentic Demo Showcase
GitHub Repo: [link-to-your-repo] # Will paste it later on!
Model: meta-llama/Meta-Llama-3.1-70B-Instruct-fast (Nebius AI)
Backend: Modal Labs
Frontend: Hugging Face Gradio
Thank You! If you're reading this — thank you for checking out our project. We hope you found it insightful and well-built.