A user-generated data based approach to enhancing location prediction of financial services in sub-Saharan Africa
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
The recent increase in user-generated content and social media adoption in developing countries offers an unprecedented opportunity to better understand the accessibility and spatial distribution of financial services in sub-Saharan Africa. Financial inclusion has been identified as a priority by multiple agencies in the region and on-the-ground efforts are currently underway to identify previously unknown financial access points in numerous developing African countries. Existing techniques for estimating the location of these access points rely on spatial analysis of often outdated or unsuitable publicly available datasets such as population density, road networks, etc., as well as expensive and time consuming surveys of locals in the region. In this work we propose an approach to augment existing spatial data analysis techniques through the inclusion of user-generated geo-content and geo-social media data. Through a comparison of standard regression models and machine learning techniques, this work proposes the use of alternative data sources to build prediction models for identifying financial access locations in countries where current estimation models are insufficient. With a better understanding of geospatial distribution patterns this work aims at reducing data acquisition costs and providing decision makers with critical data more quickly and efficiently. Finally, we present a mobile application built on the outcomes of this analysis that is currently being used to better inform on-the-ground data collection efforts.
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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.003 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 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