customer-complaint-insights

namitjain123/customer-complaint-insights
★ 0 stars Python Data/Analytics Updated today
LLM pipeline that turns CFPB consumer complaints into a labelled dataset and executive charts. Unlike typical "extract → cluster → done" pipelines, clustering quality is measured against real CFPB category labels (ARI 0.36) rather than assumed — includes an interactive Streamlit UI and an MCP server for external tool access.
View on GitHub → 🔍 Audit Wallet Slippage →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "customer-complaint-i": {
      "command": "uvx",
      "args": [
        "customer-complaint-insights"
      ]
    }
  }
}

Or install with pip: pip install customer-complaint-insights

📊
Working with market or time-series data?
The Polymarket Historical Dataset — 18.5M+ price snapshots across 18,600+ prediction markets (CSV + SQLite). Built for backtesting & ML.
View dataset →