Predicting Individual Substance Abuse Vulnerability Using Machine Learning Techniques

Substance abuse is the unrestrained and detrimental use of psychoactive chemical substances, unauthorized drugs, alcohol. Continuous these substances can ultimately lead a human to disastrous consequences. As patients display high rate relapse, prevention at an early stage be effective restraint. We therefore propose binary classifier identify any individual’s present vulnerability towards substance by analyzing subjects’ socio-economic environment. have collected data questionnaire which created after carefully assessing commonly involved factors behind abuse. Pearson’s chi-squared test independence used key feature variables influencing Later we build predictive classifiers using machine learning classification algorithms on those variables. Logistic regression trained with 18 features predict individual best accuracy.