Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{177230,
        author = {Edamalapati Mothilal Chowdary and C Harsha Vardhan and Jangalapalle Rajesh and Kuruba Teja and L Vijaya Kumar and M E Palanivel},
        title = {Predicting Substance Consumption Patterns Using Behavioral Analytics and Demographic Details},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {8864-8870},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=177230},
        abstract = {Drug dependence remains an acute public 
health problem worldwide, affecting individuals, families 
and communities at large. Traditional identification of 
dangerous drug users using indicators of behavior and 
demographics is not accurate and scale inefficient in time.  
Based on this research automatic prediction of soft and 
hard drug consumption based on mission learning models 
instead of behavior and demographic indicators is 
suggested.  By using two of the best performing classifiers, 
Random Forest and XGBoost, we were able to build a 
robust system that was able to classify effectively between 
users and non-users. Our system is comprised of several 
steps such as preprocessing, feature selection, model 
training, evaluation and visualization. The best testing 
accuracy for the Random Forest classifier was 94% on 
that of XGBoost followed closely at 93%. We also utilized 
major evaluation criteria like precision, recall, F1-Score, 
ROC-AUC, and confusion matrices to validate 
performance. These models were also integrated into a 
web based system, merging a Django back end with a front 
end created using HTML, CSS and Javascript. This 
framework has several prominent public health, 
psychological intervention and law enforcement 
applications. Overall it is an accessible tool that enables 
early intervention and policy development, blending 
behavioral science and artificial intelligence to better 
address substance abuse.},
        keywords = {Random Forest, XGBoost, Machine  Learning, Drug/Substance Consumption.},
        month = {May},
        }