Ethiopian Financial Data Hub

The Ethiopian Financial Data Hub (EFDH) is Ethiopia's comprehensive gateway to its financial ecosystem, powered by agentic AI. The platform aggregates data from hundreds of financial institutions across the country, providing insights into banks, insurance companies, microfinance institutions, digital payment providers, and capital markets. At its core, EFDH uses autonomous LLM-based agents to transform 'dark data' scattered PDFs, images, and unstructured reports into structured, API-ready datasets. An integrated AI assistant enables users to query financial data and get insights in Amharic, Afaan Oromo, and Tigrigna the three most widely spoken languages in Ethiopia. From traditional banks to innovative fintech solutions, the AI pipeline continuously discovers, extracts, and validates financial metrics with minimal human intervention. The platform features a Financial Directory, live exchange rates from banks and forex bureaus, economic indicators, a Knowledge Base, and news updates.

The primary obstacle was 'Unstructured Data Fragmentation.' In the Ethiopian financial landscape, standard APIs for exchange rates or bank performance are virtually non-existent. Data is often published as low-resolution images or diverse PDF formats daily. The AI system needed to automate the collection, extraction, and validation of this data with near-perfect accuracy to maintain trust. Additionally, the agents had to handle Amharic and English mixed content, varying document layouts, and inconsistent formatting across hundreds of sources.

We built a cutting-edge 'Agentic AI' pipeline with specialized LLM-based autonomous agents. Each agent has a defined role: one scrapes and monitors banking portals, another parses unstructured documents using vision-capable models for images and tables, and a third performs multi-step cross-validation against historical data to flag anomalies. The agents operate on a schedule with human-in-the-loop review for edge cases. We implemented a RAG-enhanced Knowledge Base for contextual retrieval and used fine-tuned extraction prompts for Ethiopian financial terminology. The AI assistant is powered by multilingual LLMs, supporting natural language queries and responses in Amharic, Afaan Oromo, and Tigrigna, enabling inclusive access to financial intelligence across Ethiopia's diverse linguistic landscape. The frontend was developed with Next.js 16+, utilizing Server Components for high-speed delivery of complex charting data, while a Django-based REST API manages the historical time-series database.

Built with

1. 01100% automated daily ingestion of exchange rates from 20+ banks via AI agents
2. 0298%+ accuracy in automated parsing of unstructured financial PDF reports using LLM vision
3. 03AI assistant supports Amharic, Afaan Oromo, and Tigrigna for inclusive financial literacy
4. 04Agentic pipeline reduced manual data entry by over 40 hours per week for analysts
5. 05RAG-powered Knowledge Base enables natural language queries over Ethiopian financial data
6. 06Rapidly established as the 'Single Source of Truth' for Ethiopian macroeconomic indicators at data.stockmarket.et