Logo Lanfrica
  • Accueil
  • Atlas
  • Analyses
  • Documentation
  • Sign in

© 2026 Lanfrica. Tous droits réservés. Tous les droits d'auteur des ressources affichées sur le site Web Lanfrica appartiennent aux détenteurs de droits d'auteur d'origine, sauf indication contraire explicite.

MariyaEA/ethiopia-financial-inclusion-forecast

Domaine:

socioeconomic

Type de record:

project
Créateur:
Mar
Hôte:
# Forecasting Financial Inclusion in Ethiopia A reliability-focused, transparent forecasting system that helps finance-sector stakeholders understand Ethiopia's financial inclusion trajectory and explore bounded Access and Usage scenarios for 2025-2027. > **Week 12 improvement objective:** transform the Week 11 analysis into a production-grade portfolio project built around reproducibility, automated testing, transparent forecasting, data-quality controls, and decision-ready communication. ## Business Problem Ethiopia's digital-finance ecosystem is expanding rapidly, but growth in registrations and transaction activity does not automatically translate into broad, active, and equitable financial inclusion. The project supports three stakeholder groups: - **Development finance institutions:** identify high-impact investment gaps and monitor inclusion outcomes. - **Mobile money operators:** plan activation, interoperability, merchant, agent, and underserved-market initiatives. - **National Bank of Ethiopia:** assess policy progress and identify risks related to access, active usage, trust, affordability, and inclusion gaps. The decision problem is therefore not simply *how many accounts exist*, but whether new infrastructure and products are converting into **unique-adult Access** and **meaningful Usage**. ## Solution Overview The project provides a transparent decision-support workflow: 1. Validate the unified financial-inclusion dataset and surface data-quality risks. 2. Separate demand-side outcomes from supply-side scale indicators. 3. Fit a simple bounded logit trend appropriate for sparse percentage data. 4. generate pessimistic, base, and optimistic scenarios with explicit adjustments. 5. Present results, assumptions, risks, and downloadable outputs in Streamlit. 6. Run automated linting and tests on every push and pull request. The model intentionally favors explainability over complexity. With only five official account-ownership survey point …

Visit

github.com

Licenses

MIT