TITLE:
Machine Learning Methods for Finding the True Owner of a Land in Kumasi (Ghana)
AUTHORS:
Lebi Jean-Marc Dali
KEYWORDS:
Land Disputes, Land Conflicts, Solution, Machine Learning Algorithms, Land Ownership
JOURNAL NAME:
Advances in Artificial Intelligence and Robotics Research,
Vol.1 No.1,
August
26,
2025
ABSTRACT: The objective of this work is to determine the true owner of a land—public or private—in the region of Kumasi (Ghana). For this purpose, we applied different machine learning methods to the ZEF (Center for Development Research) dataset on Land plots in Kumasi. Machine learning is a field in artificial intelligence that has been applied to many domains successfully in other continents. The machine learning algorithms considered are Polynomial Regression, Softmax Regression, Naïve Bayes, Bagging, Neural Network, Decision Tree, Random Forest, k-Nearest Neighbor and Support Vector Machines. In addition, we designed a rule-based convolution algorithm from these aforementioned algorithms, which performs excellently on the given dataset. In fact, our proposed model performs better than the cited models on the Kumasi dataset. This research is not trivial given the conflicts generated by land ownership issues in the sub-Saharan Africa region as a whole and in Ghana particularly. Therefore, we hope this work will help buyers be more alert in ascertaining the true ownership of a land before purchasing it.