Combining survey and census data for improved poverty prediction using semi-supervised deep learning
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
This paper presents a methodology for predicting poverty using semi-supervised learning techniques, specifically pseudo-labeling, and deep learning algorithms. Standard poverty prediction models rely on limited household survey data, whereas our approach exploits large amounts of unlabeled census data to improve prediction accuracy. By applying pseudo-labeling, we improve key performance metrics across various African regions, where our models outperform conventional approaches to identifying poor individuals. Deep neural networks (DNNs) trained on pseudo-labeled data exhibited area under the curve (AUC) scores ranging from 0.8 to over 0.9, a notable improvement over previous machine learning survey-based methods. Furthermore, random undersampling was key to refining model performance, balancing higher coverage with some reduction in precision. These findings have significant implications for poverty targeting, enabling more accurate identification of poor individuals and supporting better resource allocation. • Semi-supervised learning techniques like pseudo-labeling leverage large amounts of unlabeled census data, outperforming traditional methods that rely on limited survey data for poverty prediction. • Pseudo-labeling improved key metrics across various African regions, demonstrating superior performance in predicting poverty among diverse populations. • Deep neural networks (DNN) trained on pseudo-labeled data surpassed traditional models, achieving AUC scores ranging from 0.8 to over 0.9. • Random under-sampling and Bayesian optimization were critical for improving the DNN model’s coverage and AUC, although this came with a trade-off between higher coverage and reduced precision. • Implications for poverty targeting include more accurate identification of poor individuals, leading to better resource allocation and more effective anti-poverty interventions.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 it