lielina-pro/ethiopia-fi-forecast

# Ethiopia Financial Inclusion Forecasting Forecasting system for Ethiopia's digital financial transformation, built for a consortium of development finance institutions, mobile money operators, and the National Bank of Ethiopia. Forecasts two Global Findex-defined dimensions for 2025–2027: 1. **Access** — Account Ownership Rate 2. **Usage** — Digital Payment Adoption Rate ## Project status - [x] Task 1 — Data Exploration & Enrichment - [x] Task 2 — Exploratory Data Analysis - [x] Task 3 — Event Impact Modeling - [x] Task 4 — Forecasting Access and Usage - [x] Task 5 — Dashboard Development ## Repository structure ``` ethiopia-fi-forecast/ ├── .github/workflows/ # CI (unit tests) ├── data/ │ ├── raw/ # Starter dataset + reference codes (unmodified except enrichment) │ ├── processed/ # Analysis-ready data │ └── data_enrichment_log.md ├── notebooks/ # Analysis notebooks (Task 2+) ├── src/ # Reusable Python modules ├── dashboard/ # Streamlit app (Task 5) ├── tests/ # Unit tests ├── models/ # Saved forecasting models (Task 4) ├── reports/figures/ # Exported charts for the final report ├── requirements.txt └── README.md ``` ## Data `data/raw/ethiopia_fi_unified_data.csv` uses a **unified schema**: every row (observation, event, impact_link, or target) shares the same columns; `record_type` tells you how to interpret it. See `data/raw/SCHEMA_README.md` for the full schema design rationale and `data/raw/reference_codes.csv` for valid values of every categorical field. **Task 1 deliverables, explicitly:** - `data/raw/ethiopia_fi_unified_data_original_starter.csv` — the untouched 57-record starter dataset (kept for before/after comparison). - `data/processed/enriched_dataset.csv` — the final 69-record enriched dataset (starter + 12 new, sourced records) used by all analysis from Task 2 onward. - `data/data_enrichment_log.md` — t …