Back to Projects Compliance

Industry Classifier

Industry classification with risk assessment. Official registry connectivity and adverse media screening.

The Problem

Manual industry classification for compliance is slow, inconsistent, and error-prone. Analysts spend hours searching registries and cross-referencing sources to assess business risk.

The Solution

An AI-powered classification system that searches official business registries, scrapes web presence, and maps activities to industry codes. A second agent assesses risk based on configurable business rules.

Architecture

%%{init: {'theme': 'dark', 'themeVariables': { 'fontFamily': 'Inter', 'secondaryColor': '#1e293b', 'primaryColor': '#3b82f6', 'primaryBorderColor': '#60a5fa' }}}%% graph TB subgraph Input ["Input"] A["Company Data"] end subgraph Processing ["Processing Pipeline"] A --> B["Web Search"] A --> C["Registry Lookup"] B --> D["Code Validation"] C --> D D --> E["LLM Classification"] E --> F["Risk Assessment"] end subgraph Output ["Output"] F --> G["Result<br/>+ Risk Level"] end classDef default fill:#0f172a,stroke:#334155,color:#fff,stroke-width:1px; classDef agent fill:#0f172a,stroke:#3b82f6,color:#fff; classDef process fill:#0f172a,stroke:#334155,color:#fff; class E,F agent; class B,C,D process;
AI Agent
Process Step

Tags

PythonLangChainRisk Assessment

Outcomes

  • 90% classification accuracy with official registry connectivity
  • Processing time under 1 minute per company
  • Deployed in production for enterprise client (Amex)