View metadata
| dc.title | Where are the Unbanked in Belize?: Using Machine Learning Small Area Estimation to Improve Financial Inclusion Geographic Targeting |
| dc.contributor.author | Hersh, Jonathan |
| dc.contributor.author | Martin, Lucia |
| dc.contributor.author | Leslie, Janelle |
| dc.contributor.orgunit | Country Department Central America, Haiti, Mexico, Panama and the Dominican Republic |
| dc.coverage | Belize |
| dc.coverage | Central America |
| dc.date.available | 2021-07-09T02:00:00 |
| dc.date.issue | 2021-07-09T00:00:00 |
| dc.description.abstract | This study aims to contribute to the efficient and effective implementation of Belize's National Financial Inclusion Strategy (NFIS) that was launched by the Central Bank of Belize in 2019. It employs Machine Learning Based Small Area Estimation to develop granular estimates of Financial Inclusion at the smallest geographical level know as Enumeration Districts (ED) that were previously unavailable for Belize. To gain deeper understanding of the populations financial characteristics at the ED level, we build five measures of access to banking and financial services. Significant clustering of financial inclusion metrics that are not apparent in the district level averages are identified. This study also analyzes the factors that influence the use of financial services and instruments in order to propose appropriate adjustments in the strategies implemented by authorities in each geographical area. Both the spatial distribution of Financial Inclusion indicators and the factors influencing the adoption of financial services shed light on specific recommendations relevant to each of the four Thematic Financial Inclusion Task Forces included in the NFIS. |
| dc.format.extent | 38 |
| dc.identifier.doi | http://dx.doi.org/10.18235/0003381 |
| dc.identifier.url | https://publications.iadb.org/publications/english/document/Where-are-the-Unbanked-in-Belize-Using-Maching-Learning-Small-Area-Estimation-to-Improve-Financial-Inclusion-Geographic-Targeting.pdf |
| dc.language.iso | en |
| dc.medium | Adobe PDF |
| dc.publisher | Inter-American Development Bank |
| dc.subject | Machine Learning |
| dc.subject | Social Innovation |
| dc.subject | Financial Inclusion |
| dc.subject | Financial Service |
| dc.subject | Geographic Information System |
| dc.subject.jelcode | O31 - Innovation and Invention: Processes and Incentives |
| dc.subject.jelcode | G21 - Banks • Depository Institutions • Micro Finance Institutions • Mortgages |
| dc.subject.jelcode | D14 - Household Saving; Personal Finance |
| dc.subject.jelcode | O35 - Social Innovation |
| dc.subject.jelcode | G51 - Household Saving, Borrowing, Debt, and Wealth |
| dc.subject.jelcode | G53 - Financial Literacy |
| dc.subject.keywords | big data;machine learning;financial inclusion;Central America;Belize;geographic information systems;small area estimation;social innovation;geographic targeting |
| dc.type | Monographs |
| idb.identifier.pubnumber | IDB-MG-00939 |
| idb.operation | BL-P1103 |