Predicting Household's Mobile Banking Saving Behavior in Western Kenya: An Algorithmic Approach
Bibliographic record
Abstract
ABSTRACT Digitalization holds promises to unlock savings accumulation in Africa. This paper predicts the mobile savings, taking advantage of machine learning to examine a massive set of features known theoretically and empirically to affect household savings behavior. The algorithm fits a generalized regression model through a penalized maximum likelihood. The work anchors in economic theory on savings but differs from the method standpoint to elicit mobile banking savings take-up and savings accumulation. Data covered thirty-six villages in Western Kenya. Predictors clustered into livelihoods, assets inventory, formation and use of assets, income generation and its use, food composition, intake and nutrition, the housing quality and tenureship, water and sanitation, energy use, family structure, social status architecture, adverse shocks to agricultural production (crop and livestock loss events) and demographics. Data include 1600 households from six different communities and 7,700 quarterly observations from 2013 to 2015. Although the results point to shreds of evidence that corroborate previous findings, we highlight in this paper mobile banking's role in the savings accounts ownership and savings accumulation, as well as the effects of age and employment status. Mobile phone ownership is a strong and significant predictor of savings account ownership. However, the mobile phone is a vehicle to fluctuating savings balance and encourages dissaving. Moreover, being young and in the workforce increases the mobile banking savings take-up but also the dissaving behavior, compared to older age group. This work subsets features that could improve product or policy design towards a better financial inclusion of rural poor.
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 | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 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".