Optimizing infrastructure resource allocation in rural areas using clustering and decision tree analysis: a case study of Golestan Province, Iran
This study explores applying advanced data mining techniques, specifically K-means Clustering and decision tree analysis, to optimize infrastructure resource allocation in rural areas. Focusing on villages in the eastern region of Golestan Province, Iran, this research addresses significant infrastr...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-12-01
|
| Series: | Sustainable Futures |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666188825006410 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | This study explores applying advanced data mining techniques, specifically K-means Clustering and decision tree analysis, to optimize infrastructure resource allocation in rural areas. Focusing on villages in the eastern region of Golestan Province, Iran, this research addresses significant infrastructural challenges, including water shortages, inadequate road networks, unreliable electricity supply, and ineffective implementation of rural development plans. The audience, as policymakers, researchers, and stakeholders in rural development and infrastructure management, play a crucial role in this research. The survey data was from 244 villages, and the K-Means clustering method identified five unique clusters of infrastructure issues. Decision tree analysis, subsequently applied to these clusters, achieved an overall prediction accuracy of approximately 49 %, identifying key influential factors such as village population size and severity of the reported problems. The results demonstrate that integrating clustering and decision tree techniques can significantly enhance resource allocation decisions' effectiveness, enabling strategically prioritizing resources and addressing the most pressing infrastructural challenges in rural communities. This data-driven approach contributes to sustainable rural development and better-informed policymaking, with involvement being integral to its success. |
|---|---|
| ISSN: | 2666-1888 |