A Model for Predicting the Impact of Alcoholism and Drug Abuse on Students’ Academic Performance Using Machine Learning Techniques

Nowadays, the illicit consumption of drugs and alcohol by Nigerian youths has a substantial impact on both their academic performance and society at large.In order to help find solutions that can shield students from the disturbing problem of alcoholism and drug abuse, machine learning (ML) techniques that are capable of predicting the risks that Nigerian students might fall prey to drug and alcohol addictions, which could affect their academic performance was deployed.Data regarding the impact of alcoholism and drug abuse among students were gathered through a field survey from different tertiary institutions across Nigeria.Two renowned machine learning methods -Support Vector Machine (SVM) and Random Forest (RF) were applied to the preprocessed dataset collected for our survey.An optimizer was employed to achieve the best optimization function for the deployed machine learning models.The performance and effectiveness of both ML classifiers were evaluated in order to determine which of them has the best prediction accuracy and error rate using several well-known ML evauation metrics.