<![CDATA[Internal displacement in Nigeria remains a major humanitarian challenge, driven by conflict, insurgency, communal clashes, and climate-related disasters, yet existing responses are often reactive and inadequate for proactive planning. This study, titled Data-Driven Modelling and Predictive Analysis of Internal Migration and Displacement Trends in Nigeria for Enhanced Humanitarian Planning, applies a machine learning framework to displacement data to forecast trends and support timely humanitarian interventions. Using datasets from the International Organization for Migration’s (IOM) Displacement Tracking Matrix, particularly the Baseline Assessment and Needs Monitoring surveys, the research processed over 114,000 records across 19 variables, including demographic indicators, site accessibility, household size, and priority needs. Data preprocessing involved handling missing values, categorical standardization, one-hot encoding, and normalization of numeric features, with attention to balancing the skewed distribution of displacement reasons where insurgency accounted for 95% of cases, communal clashes 4%, and natural disasters 1%. Exploratory analysis revealed that Borno, Adamawa, and Yobe states remain most affected, with insurgency consistently dominating and September 2022 marking the highest peak in displacement. Three algorithms: Logistic Regression, Random Forest, and XGBoost were evaluated, with XGBoost outperforming others by achieving a macro F1-score of 0.96, and balanced accuracy of 0.968 across classes. The model correctly classified nearly all insurgency cases and demonstrated strong performance for communal clashes (F1-score = 0.99) and natural disasters (F1-score = 0.90). These findings show that displacement follows identifiable socio-economic and geographic patterns, and predictive modeling can capture them effectively.]]>
Copyrights © 2026
