• B Suneetha
• Mrs V Dakshayani

Depression is a major mental health concern often underdiagnosed due to subjective assessments and social stigma. Traditional diagnostic methods relying on clinical interviews and surveys are time-consuming and prone to bias. To overcome these limitations, this study proposes a Stacking Machine Learning Model that integrates SVM, KNN, and LightGBM as base learners, with Logistic Regression as the meta-classifier. The dataset includes socio-economic and lifestyle factors such as age, gender, marital status, income, and living expenses. After preprocessing using missing value handling, normalization, and feature correlation analysis, the stacking ensemble effectively combines the strengths of individual models—capturing nonlinear relations, locality-based learning, and complex feature interactions. Experimental results show that the proposed model outperforms individual classifiers in accuracy, precision, recall, and ROC-AUC, providing an efficient tool for early depression prediction and supporting data-driven mental health interventions.

DEPRESSION PREDICTION USING STACKING MACHINE LEARNING MODEL

"DEPRESSION PREDICTION USING STACKING MACHINE LEARNING MODEL", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 11, page no.a745-a752, November-2025, Available :http://www.jetir.org/papers/JETIR2511086.pdf

"DEPRESSION PREDICTION USING STACKING MACHINE LEARNING MODEL", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 11, page no. ppa745-a752, November-2025, Available at : http://www.jetir.org/papers/JETIR2511086.pdf