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.

habilm-analytics/tanzania-best-ml-forecasting

Domaine:

education

Type de record:

project
Créateur:
hab
Hôte:
End-to-end ML pipeline forecasting Tanzania CSEE pass rates · BEST 2020–2024 · 12 models · Streamlit dashboard · 2025–2030 forecast # Forecasting Education Performance Using Machine Learning ## An End-to-End Analysis of Tanzania BEST Datasets (2020-2024) > **Author:** Habil Masawika > **Domain:** Education Analytics | Machine Learning | Public Policy > **Status:** Complete portfolio project --- ## Project Overview This project builds a production-quality, end-to-end machine learning pipeline that predicts and forecasts secondary school examination performance in Tanzania using five years of national administrative education data from the Ministry of Education, Science and Technology (MoEST). The Certificate of Secondary Education Examination (CSEE) pass rate -- the primary outcome measure -- is modelled as a function of teacher supply and quality, infrastructure access, student retention, and system-scale indicators. Twelve regression models are trained and compared, the best model is tuned via cross-validated hyperparameter search, and predictions are explained using feature importance, permutation importance, and partial dependence analysis. A six-year forecast (2025-2030) is generated using three complementary methods, and all results are presented through an interactive Streamlit dashboard. ### Why This Matters Tanzania has invested heavily in secondary education expansion since 2015, with enrolment roughly doubling and CSEE pass rates rising from 68% to 89%. This project asks: *which measurable inputs drive those outcomes, and what does the trajectory look like through 2030?* The answer informs teacher deployment policy, infrastructure investment prioritisation, and regional equity planning. --- ## Dataset | Property | Detail | |---------------|--------| | Source | Ministry of Education, Science and Technology (MoEST) -- BEST Annual Reports | | Files | BEST_2020 through BEST_2024 National Data (.xlsx) | | Format | 2020: numbered tables (Table N); 2021-2024: named sheets (T3.*) | | Coverage | 26 mainland Tanzania regions x 5 years = ~130 panel obser …

Visit

github.com

Licenses

MIT

Similaires

habilm-analytics/tanzania-dml-teacher-qualityhabilm-analytics/kobo-ipv-microfinance-surveykaruribrian/agriculture-ml-predictive-analyticsSezibra/conflict-forecasting-mlJUBRIL-ADEBOGUN/ML-Commodity-ForecastingBadibossPy/Wflow-ML-Flood-Forecasting

habilm-analytics/tanzania-dml-teacher-quality

Double Machine Learning (DML) framework for causal inference in education: Teacher quality and learn

habilm-analytics/kobo-ipv-microfinance-survey

Academic research questionnaire digitization project using KoboToolbox and XLSForm for mobile-based

karuribrian/agriculture-ml-predictive-analytics

Machine learning models for predicting crop yield and rainfall trends in Kitui County, Kenya. Includ

Sezibra/conflict-forecasting-ml

Sub-national conflict forecasting for Ethiopia using Random Forest, temporal cross-validation, and S

JUBRIL-ADEBOGUN/ML-Commodity-Forecasting

Can you accurately forecast weekly market prices for maize in Kenya?. ccurate forecasts will help fa

BadibossPy/Wflow-ML-Flood-Forecasting

Catalog-independent Wflow SBM hydrological model for the Upper Niger Basin. Complete ETL pipeline fr