Reproducibility package for Human Capital Expenditure And Its Effectiveness On Multi-Programme Coverage: A Policy Prioritization Investigation
Overview
This paper uses AI-enhanced agent computing to determine how to allocate budgetary resources within a large set of heterogeneous government programs targeting human capital.
Our approach considers essential features of the budget allocation process: multidimensionality, interdependencies between policy issues, and the political economy of public officials' collective action.
We use highly disaggregated Mexican data covering the 2016-2022 period across 49 human capital programs of the federal government and focus on how expenditure affects program coverage (the proportion of the population with a public problem and who has access to various government benefits to mitigate those problems) in the short run.
We answer the following research questions: how sensitive is program coverage to changes in public expenditure?; what are the structural bottlenecks behind poor coverage response?; and what are the optimal budgetary allocations that could boost the performance of a multidimensional objective function?
Reproducibility Package
| Repository name | URI |
|---|---|
| Reproducible Research Repository (World Bank) | https://reproducibility.worldbank.org |
Reproducibility
Paper exhibits were reproduced on a computer with the following specifications:
• OS: Windows 11 Enterprise
• Processor: Intel(R) Xeon(R) Gold 5218 CPU @ 2.30GHz, 2300 Mhz, 4 Core(s), 4 Logical Processor(s)
• Memory available: 8.15 GB
• Software version: Python 3.10
Runtime: 20 minutes
The package uses intermediate data. The code used to process the raw data into intermediate data is included in the package for transparency; however, reviewers did not verify this portion of the workflow because some of the dependencies required to run the data-construction code are no longer available. Instead, reviewers verified the outputs generated from the intermediate data included in the package.
To reproduce the exhibits in this paper, users should:
- Restore the software environment using
requirements.txt. - Run
main.py.
Outputs will be generated in thefiguresandtablesfolders.
Data
All data sources are publicly available and included in the reproducibility package.
Description
| Author | Affiliation | |
|---|---|---|
| Omar A. Guerrero | University of Helsinki | omar.guerrero@helsinki.fi |
| Michael Weber | World Bank | mweber1@worldbank.org |
| Daniele Guariso | CMCC Foundation - Euro-Mediterranean Center on Climate Change | daniele.guariso@gmail.com |
| Gonzalo Castañeda | Centro de Investigación y Docencia Económicas (CIDE) | sociomatica@hotmail.com |
2026-05-19
Scope and coverage
| Location | Code |
|---|---|
| Mexico | MEX |
Disclaimer
The materials in the reproducibility packages are distributed as they were prepared by the staff of the International Bank for Reconstruction and Development/The World Bank. The findings, interpretations, and conclusions expressed in this event do not necessarily reflect the views of the World Bank, the Executive Directors of the World Bank, or the governments they represent. The World Bank does not guarantee the accuracy of the materials included in the reproducibility package.
Access and rights
| Name | URI |
|---|---|
| MIT License | https://opensource.org/license/mit |
| World Bank IGO Rider | https://github.com/worldbank/metadata-editor/blob/main/WB-IGO-RIDER.md |
Contacts
| Name | Affiliation | |
|---|---|---|
| Omar A. Guerrero | University of Helsinki | omar.guerrero@helsinki.fi |
| Reproducibility WBG | World Bank | reproducibility@worldbank.org |
Information on metadata
| Name | Abbreviation | Affiliation | Role |
|---|---|---|---|
| Reproducibility WBG | DECDI | World Bank - Development Impact Department | Verification and preparation of metadata |
2026-05-19
1