Mining good-looking understanding from accrued set of statistics stays constantly exciting. A number of researchers have furnished new offerings to this trouble via massive awesome perspectives. Several human beings don`t recognise how human beings get Addicted to Drug Consumption Risk (ADCR). They misleadingly recognize that individuals who consume drugs include deficiency in moral moralities and self-control. But the actual certainty is that the ADCR is a complicated disease. It additionally makes tough in quit from drug consumption and makes tougher in opposition to precise intents and will power. This is due to the fact the drug make modifications in brain in opposition to not consuming the drug. Modern study methodologies offer beneficial in understanding approximately how drug disturb the mind. It additionally classifies appropriate remedies to get over drug consumption to lead a peaceful life. In our approach the drawback in extraction of insightful understanding from statistics is estimated as crucial task. This study also lookout for competent datamining (DM) strategies to categorise the drug users and non-drug users based totally on drug consumption behaviour. Further targeted evaluation concerning eradication of dependency to drug consumption via analysing the features and appropriate measures are advised via this study. Three of the machine learning (ML) algorithms Decision Tree (DT), Support Vector Machine (SVM) and K-Nearest Neighbor (K-NN) are considered for implementation. From the data set information regarding drug consumption related to nervous function affective psychoactive five drugs (Alcohol, Caffeine, Cannabis, Cocaine, Heroin and Nicotine) was considered. The 70 % of dataset is divided to construct the training set and 30 % is for testing set. Finally, the Accuracy, AOC and the time occupied to construct the model are retrieved as classification results to achieve this research. The DT algorithm produces best result for the drug Alcohol (94.33). The SVM algorithm provide best results for the drugs Caffein (98.76), Cannabis (92.03), Cocaine (96.99), Heroin (97.52) and Nicotine (88.85). Among the five factor features the Nscore, Oscore and Cscore provide better contribution to identify the drug consumption risk. The ROC curve (AUC) for all the drugs [Alcohol (0.96), Caffein (0.93), Cannabis (0.98), Cocaine (0.92), Heroin (0.96) and Nicotine (0.97)] the SVM Classification Model provide the best accuracy. From our model it is observed that among the 12 features Age, Neuroticism, Sensation Seeking, Oscore and Cscore contribute higher to predict the drug consumption risk. So, more personality trails are to be conducted by considering the contributing features.

Drug, Decision Tree, SVM, K_NN, Drug Consumption Risk, AUC.