Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

bemnetne/new-ethiopia-fi-forcast

Domain:

socioeconomic

Record type:

project
Creator:
bem
Host:
# Ethiopia Financial Inclusion Forecasting A finance-focused data and machine learning project that analyzes historical financial inclusion in Ethiopia, models major market and policy events, forecasts Account Ownership and Digital Payment Usage for 2025–2027, and presents results through an interactive Streamlit dashboard with SHAP-based explainability. ## Business Problem Financial institutions, development organizations, mobile network operators, and policymakers need reliable evidence on how financial inclusion in Ethiopia may evolve. Available information is scattered across surveys, regulatory reports, telecom announcements, and payment-system records. This makes it difficult to answer practical questions such as: - Will Ethiopia reach its Account Ownership target? - Will Digital Payment Usage grow faster than Access? - Which policy and market events may influence progress? - What risks could prevent forecast outcomes from being achieved? - Which demographic groups remain underserved? This project combines those sources into a structured analytical workflow that supports planning, scenario analysis, and risk-aware decision-making. ## Solution Overview The project follows an end-to-end workflow: 1. Collect and validate financial inclusion observations and market events. 2. Standardize records into a unified dataset. 3. Explore Account Ownership, mobile-money penetration, gender, location, and payment-use trends. 4. Model event direction, magnitude, and expected lag. 5. Forecast Account Ownership and Digital Payment Usage for 2025–2027. 6. Build pessimistic, base, and optimistic scenarios. 7. Add uncertainty ranges and target-gap analysis. 8. Train an explainable Ridge regression model on Global Findex subgroup data. 9. Generate global and local SHAP explanations. 10. Present metrics, forecasts, risks, and business implications in a Streamlit dashboard. 11. Validate core functions with automated tests and GitHub Actions. ## Key Results - Account Own …

Visit

github.com