School Governance and Learner Performance in Sub-Saharan Africa: A Neural Networks Approach
Bibliographic record
Abstract
The aim of this paper is to analyse the impact of school governance on learner performance in Sub-Saharan Africa, in the face of persistent low performance in the region, revealed by the PASEC 2019 report. The study uses an econometric model followed by machine learning models (Regression Logistic, Random Forest, Extra Tress Classifier, Extreme Gradient Boosting, Artificial Neural Networks) to explore the relationships between school results and governance factors measured by school management, pedagogical practices and relations with stakeholders. The results show that artificial neural network models perform better than conventional approaches in terms of accuracy and explainability. Explainability by Shapley values shows that the quality of administrative and pedagogical management, benevolent school-student relations, and activities to promote the best students significantly improve performance. The study suggests capacity building for managers in order to improve the quality of administrative and pedagogical management. It also highlights the need to promote rigorous administrative governance, based on effective practices and adapted to local realities. In addition, specific strategies should be put in place to reward high-performing students, while encouraging professional collaboration between education stakeholders. Finally, a review of parental involvement practices is recommended in order to avoid inappropriate expectations likely to be detrimental to learners’ performance.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".