Marketing · Consumer Behaviour · Machine Learning
Predicting Consumer Purchase Intention on Social Commerce Platforms: A Hybrid Machine Learning and Advanced Econometric Approach
Pankaj Kumar Tiwari, Vikrant Veer Singh Pathania — Shoolini Business School, Shoolini University
Integrating advanced machine learning with structural econometrics, this study models consumer purchase intention on Instagram and other social commerce platforms in India. On a primary dataset of 412 respondents across four metropolitan areas, a Probit model with average marginal effects is benchmarked against six ML classifiers. Gradient Boosting (XGBoost) achieves 89.1% accuracy and AUC-ROC 0.941, while social media engagement and influencer credibility emerge as the strongest determinants of purchase intention. A SHAP–Probit convergence analysis (Spearman ρ = 0.91) confirms methodological complementarity.


