Abstract

Developing countries like Nigeria are yet to recover from the effect of the COVID-19 pandemic in the various sectors of the economy especially as it relates to food security. This study examines the performance of the Support Vector Machine (SVM) method and the Random Forest (RF) Classification Method in predicting the impact of the COVID-19 pandemic on food security in Anambra State, Nigeria. The measure for food security in this study includes Crop Production (CP), Livestock Production (LP), Forestry Production (FP1) and Fishery Production (FP2) while the demographic predictors considered in the study were Age interval, Marital Status, Gender and Educational Qualification. The population of the study comprised all the farmers in Anambra State, Nigeria. A multi-stage sampling technique was used in determining the adequate sample size for the study. The tools employed for the analysis were the SVM, RF and the Wilcoxon signed rank test. The findings of the study showed that there is no significant difference between the accuracy measures from the two classifiers since the p-value of the Wilcoxon signed rank test was obtained as 0.125. Further findings showed that Educational Qualification (MSE=6.67%) was found to be the most important predictor for the estimation of CP while Gender (MSE=-1.27%) was the least important predictor; Age interval (MSE=10.16%) was found to be the most important predictor for the estimation of LP while Gender (MSE=-3.71%) was the least important predictor; Gender (MSE=8.20%) was found to be the most important predictor for the estimation of FP1 while Age interval (MSE=3.36%) was the least important predictor, Marital Status (MSE=3.10%) was found to be the most important predictor for the estimation of FP2 while Educational Qualification (MSE=-3.92%) was the least important predictor. The study concludes that any of the methods can be employed in estimating the impact of COVID-19 on food security in the study area.